Category Focus/categories/automation
Automation AI Tools
Discover and compare the best automation AI tools and software. Browse 632+ curated tools with reviews and rankings.
Projects tracked
632
Sort mode
RECENT
Page
2
Automation
Invited is an AI reminder scanner that turns any document containing a date into a smart reminder. Bills, cheques, renewals, invitations and appointments are all fair game: you snap a photo, pick a screenshot or PDF, or share a document from another app, and Invited's AI finds every date on it so you can be reminded before it matters. It runs on iPhone and Android, requires no signup, and is made for anyone who wants a simple, reliable way to stay ahead of due dates, renewals and events. The trouble with dates is that they arrive on paper, in PDFs, in screenshots and inside apps, not in a single tidy calendar. A bill carries a due date and a late-fee date; an insurance policy has a renewal date; a wedding invitation lists five separate functions across several days; a boarding pass has a departure time and a gate. Most reminder apps can only capture one date, so people end up typing entries by hand, copying amounts and times, and still missing the moment that mattered. Invited exists to close that gap: instead of asking you to remember, it scans the document and does the work of finding the dates for you. Invited accepts almost any input that contains a date. You can take a photo with your camera, pick an image or screenshot from your library, choose a PDF or document from your files, or share something straight into Invited from any other app. That means the same workflow handles an electricity bill photographed on your kitchen table, a screenshot of a subscription confirmation, a PDF insurance schedule, or a boarding pass shared from your email. Because sharing is supported from any app, you do not need to export or retype anything — the document goes in as it is and the AI takes it from there. The standout capability is that one document can produce many reminders. Where most tools find a single date, Invited finds all of them. A Gujarati wedding invitation with five functions — Mehendi, Haldi, Sangeet, the wedding ceremony and the reception — becomes five separate reminders, each with its own time and place. A BrightGrid electricity bill can produce both a pay-bill reminder for the due date and a separate late-fee reminder for the later penalty date. This matters because the same paperwork often contains several deadlines that sit days or weeks apart, and catching all of them is the difference between a small task and an avoidable fee. Invited reads 80+ languages, so a document does not need to be in English to be understood. The site highlights English, Gujarati, Hindi, Arabic, Chinese, Spanish, Portuguese, Japanese and French among the supported languages. It also understands nine calendar systems: Gregorian, Vikram Samvat, Hijri, Hebrew, Chinese Lunar, Persian, Thai Buddhist, Ethiopian and Japanese era. That means a date written as Kartik Sud 5, 1 Shawwal, 1 Tishrei, the first day of the first month, 1 Farvardin, year 2569, 1 Meskerem or Reiwa 8 is converted into a real date in your own calendar, rather than being lost because it does not look like the format you are used to. You control when you hear about each reminder. Invited lets you choose a lead time of 1 hour, 6 hours, 12 hours, 24 hours or 2 days before the date. You can set a default once and then change it for any individual reminder, so a flight can warn you a day ahead while a bill nudges you 24 hours before it is due. The product notes that reminders can be set from 1 hour to 2 days before, giving you a simple range that covers both errands and events. Invited is deliberately minimal and honest about how it handles your information. There is no signup and no account — you open the app and scan. To find the dates, the document you scan is sent securely to an AI service that reads it, while your reminder list itself is stored on your device rather than in the cloud. You stay in control by reviewing every date before saving, and the app warns that AI can make mistakes with dates, times and payment locations, so you check the extracted details first. You can edit or delete reminders at any time, and unlimited reminders can also be created by hand if you prefer. The overall flow is described as three taps with zero typing. First, snap or share: take a photo, pick a screenshot or PDF, or share from any app. Second, the AI reads it, extracting dates, times, places and amounts in 80+ languages — and you check them before saving. Third, you get reminded anywhere from 1 hour to 2 days before, at the lead time you chose. Behind the scenes the app moves through a small pipeline (load, read, AI, done) and then presents the events it found for your review, with each event showing its title, date, time, place, amount and reminder offset. The benefit is straightforward. Instead of acting as a second memory, Invited removes the need to remember at all: you scan once and the reminders appear before the deadline. Bills are paid before late fees, cheques are deposited before they run out of time, insurance renewals are handled before cover ends, free trials are cancelled before you are charged, and invitations and appointments are not missed. Because everything stays on your phone and needs no account, using it is fast and low-friction — a single scan can create several reminders at once, and the reminders carry context such as the amount owed, the place, or the gate number. Invited is used across a wide range of everyday documents. Bills and utilities are scanned for due dates and late-fee dates. Cheques are scanned so you deposit them before they expire. Insurance and renewals are scanned so you act well before cover ends. Subscriptions are scanned for free-trial and renewal dates, before you are charged. Invitations — weddings, birthdays, parties and conferences — are scanned so every function on the card gets its own reminder. Appointments such as doctor and dentist visits are captured with their time and place. Travel tickets and boarding passes are scanned for departure and gate times. Warranty cards are scanned so you claim before the warranty quietly runs out. The site also lists rent, streaming subscriptions, credit card statements, passport renewals, gas bills, license renewals and school events among the things people scan. Invited is aimed at anyone who deals with dated paperwork — households paying bills, families juggling multiple invitations and appointments, travellers tracking flights and tickets, and anyone who wants a no-account reminder tool that works with documents they already have. It is available on iPhone and Android, in 80+ languages. Pricing is freemium: the app is free to download and includes 3 free AI scans, plus unlimited reminders created by hand; Invited Pro unlocks unlimited AI scans and more, with the current price shown in the App Store and Google Play. At its core, Invited is a reminder app that reads for you. It takes the documents that already carry your deadlines — bills, cheques, policies, invitations, tickets, warranties and more — and converts every date it finds into a reminder you will actually see, in your language and your calendar, with no signup and no typing.
Kudos is a free financial companion and browser extension that turns everyday spending into bigger earnings. According to its website, Kudos automatically maximizes your card offers and benefits, lowers your bills, and keeps finding new ways to save. It is built for people who hold one or more credit cards and want more value from the purchases they are already making. Instead of simply presenting charts, Kudos surfaces useful actions: it auto-activates card-linked offers, recommends the best card to use at checkout and in stores, tracks card benefits before they expire, and uses AI to negotiate bills and cancel subscriptions. Members keep 100% of the savings. The product is described as working at more than two million stores and supporting more than 3,000 credit cards, with a membership base of over 500,000 people. The problem Kudos addresses is money that quietly slips away. As the product's own material explains, most people do not know that their credit cards come with personalized offers they have to turn on by hand, and many card benefits go unused before they expire. Forgotten subscriptions keep charging month after month, and recurring bills such as internet or cellphone plans are often higher than they need to be. Kudos frames its mission around recovering that value, telling users to "take back +$3,000 in missed benefits every year" and stating that the average member earns over $3,000 per year with Kudos Premium. Most money apps, the company argues, show you charts; Kudos instead does the work of finding and recovering that value on your behalf, so saving does not depend on constant manual checking. One of the core feature groups is card-linked offer activation and rewards stacking. Kudos auto-activates card offers across issuers including Amex, Chase, BofA, Wells Fargo, and Citi, describing these as worth $750+ a year, and reminds you when to use them. Product Hunt metadata puts the figure at about $800/yr in offers in early testing. The free browser extension then works at the point of purchase: it picks the best card, autofills card details, applies offers, and stacks cash back automatically at checkout. According to the FAQ, when you visit an issuer portal such as Amex, Chase, or Citi with Kudos installed, it automatically activates hundreds of offers across all your cards with no manual clicking. At checkout, Kudos shows you active offers and recommends the card that maximizes your savings, factoring in your card's rewards rate, activated offers, and Boost Cash Back. Kudos Boost Cash Back is available at 15,000 partner stores, and Premium members earn 1.25x more Boost at those stores. A second major feature group is AI-powered bill negotiation and subscription cancellation. Kudos AI cancels unused subscriptions, negotiates your bills, and handles the calls to save you money. Kudos states that its AI calls providers to lower your bills, quoting $216/yr per negotiation, and cancels subscriptions you forgot, quoting $247/yr each. Premium members can tap "Cancel for Me," and Kudos handles the entire cancellation process — phone calls, live chat, and emails — while you get real-time status updates until it is done. Kudos also identifies and helps you negotiate bills that you might be overpaying for. The website's comparison table notes that unlike Rocket Money, which it says takes up to 10 days and up to 50% of savings, Kudos lowers your bills and cancels subscriptions with no cut taken. A member testimonial describes the AI calling a cellphone company within 12 hours of subscribing and reducing a bill from $420 to $315 a month with no plan changes. A third group of features centers on benefits tracking, spending insight, and card guidance. Kudos tracks every benefit across all your cards and makes sure you use them before they expire, backed by a promise to help members take back more than $3,000 in missed benefits every year. Kudos analyzes your transaction history and proactively finds personalized ways to earn more rewards and save money, and Premium unlocks more advanced AI insights tailored to your spending plus two years of transaction history to spot patterns and trends. A location-based Cheatsheet shows the best card to use wherever you are shopping, so you never miss a reward in-store. The free plan also includes personalized card discovery tools — Dream Wallet, Card Explore, Test Drive, and Approval Odds — and a member review notes that the Test Drive feature helped them select the right card. Finally, "Ask your wallet anything" lets Kudos AI connect the dots across your cards, bills, and spending to answer questions, uncover hidden opportunities, and take action to save you money. The overall workflow is described in four steps. First, Activate: download Kudos and connect your cards securely. Second, Connect: Kudos learns how you spend to find ways for you to earn and save. Third, Automate: activate offers, negotiate bills, and use the best card. Fourth, Earn & Save: watch your savings pile up and keep more of what you earn. Card connections are powered by Plaid, and the company emphasizes that with Plaid you choose what is shared, with whom, and for how long. Security is positioned as a priority: Kudos says it uses Zero-Knowledge Architecture so sensitive data is encrypted on your device and invisible to anyone, including Kudos; it has passed rigorous independent audits to achieve SOC 2 (Type 1) compliance; and data is protected with 256-bit encryption, the same standard trusted by banks worldwide. For users, the stated outcomes are earnings and savings with minimal effort. Kudos says the average member earns over $3,000 per year with Kudos Premium, and that Premium members on average earn an additional $754/year and save $324/year. The product currently advertises 500,000+ members, a 4.8-star rating, and 10,000+ reviews. Testimonials on the site describe auto-activated offers that actually get used, a personal finance experience "without the busywork" that surfaces useful actions instead of just charts, and negotiated savings that more than pay for a lifetime membership. One reviewer reports that the AI got their bill reduced by $50 more than the entire subscription cost within 12 hours, while another notes that Kudos brings everything into one place and saves time by removing the need for constant checking. Concrete use cases follow directly from these features. When shopping online at any of the two million-plus supported stores, the free browser extension chooses the best card for that merchant, autofills card details, applies activated offers, and stacks cash back at checkout. When shopping in person, the Cheatsheet tells you which card to use based on your location so you do not miss an in-store reward. Before a benefit expires, the Automated Benefits Tracker flags partially redeemed credits and prompts you to use them. For recurring expenses, Kudos detects subscriptions across your connected cards, helps you decide what is worth keeping, and handles cancellations end to end, while also negotiating bills you may be overpaying on. If you are considering a new card, the free discovery tools including Dream Wallet, Card Explore, Test Drive, and Approval Odds help you choose one that fits your setup. And when you want a straight answer, you can ask Kudos AI about your cards, bills, and spending. The target audience is people who use credit cards — especially those holding multiple cards or unsure which card fits their setup — and who want to capture rewards, offers, and benefits without tracking them manually. Kudos is delivered as a browser extension and a mobile app, with Product Hunt topics listing Android and Chrome Extensions alongside Fintech, Artificial Intelligence, and Personal Finance. It connects cards through Plaid and supports more than 3,000 credit cards, with offers automated for issuers including Amex, Chase, BofA, Wells Fargo, and Citi. Pricing follows a freemium model: the free plan includes seamless checkout with best card recommendations and autofill at 2M+ stores, Boost Cash Back at 15,000 stores, all rewards, credits, and benefits in one place, card discovery tools, and the Cheatsheet. Kudos Premium is sold as a $190 lifetime deal (listed as $240 total, with $50 off for a limited time) or a $141.99 yearly subscription, and includes automated benefits tracking, AI negotiations to lower bills, auto-activate card-linked offers, 1.25x more Boost at 15,000 partner stores, a 500 Boost welcome bonus for lifetime buyers, two years of transaction history and dashboards, welcome bonus tracking with smart reminders, and early access to new autopilot features. The company positions Kudos against Rocket Money, CardPointers, Rakuten, and Credit Karma, and its coverage includes Yahoo Finance, Bloomberg, Nasdaq, and The Motley Fool. In short, Kudos takes the manual work out of credit card rewards. It auto-activates offers you would otherwise have to turn on by hand, tells you the best card to use online and in stores, tracks benefits before they expire, and uses AI to negotiate bills and cancel subscriptions — all while letting you keep 100% of the savings. For cardholders who want the money they are already leaving on the table, Kudos is positioned as a set-up-once, earn-forever financial companion.
Foley is a voice-first to-do list that turns spoken thoughts into structured tasks. Instead of typing a task, choosing a project, setting a date and adding a reminder, you say a sentence — or several things at once — and Foley works out the tasks, the dates and the project before anything lands. It is built for people who keep their work and their life in one place and want the admin of task management to disappear. The app is available on Mac, Windows, the web, iPhone, Android, Apple Watch and Wear OS watches, and the same list follows you across those surfaces. Its promise is simple: out of your head, into your day. Most task apps ask you to do the filing yourself. You have to think of the task, open the app, type it, decide where it belongs, pick a date, and set a reminder — often at the exact moment your hands are full or your attention is elsewhere. That friction is why lists go stale and why thoughts get lost between one meeting and the next. Foley approaches the problem from the other direction. The thought is the input, not the chore. You say what needs doing the way you would say it to a colleague, and the app handles the structure. When two tasks could fit what you said, or when it needs to know where before it goes looking, Foley asks a question rather than making a guess, so you stay in charge of the result. Capture is where everything begins. A desktop shortcut brings Foley to you without pulling you out of what you are doing, and on iPhone, Android and the watches the capture sheet or capture mark listens while you talk. You can say one thing or several — “Add two tasks: buy milk, and call the electrician” — and Foley works out the separate tasks, the dates and the project before anything lands. You review what it understood before the tasks are saved. On the wrist, Foley shows what it is doing: while the microphone is open the wordmark pulses and the clock counts up, so waiting never looks like something is broken, and you stop when you are done. Nothing asks you to confirm. Once tasks exist, Foley gives them a place. Folders keep related projects together and projects hold the work and its context, so work, life and everything in between can live in one system with clear boundaries — “Create a folder called Clients and move work into it.” For the parts of life that are not projects, Lists provide a simple checklist: shopping, packing, the little things to remember. You can add an item to the shopping list and tick things off. Task context goes further than a title. You can connect related work, keep notes and attachments with the task, and see the dependencies that explain what comes next, such as an invoice that is blocked by a board deck. Seeing what is holding things up is part of knowing what to do next. Foley is also a planner. The Daily desk brings tasks from across your projects together in one clear place, where you can open a task, change a detail, or check it off when it is done. Your day shows the shape of the day in a calendar, so when plans change you can move a task or change its time and keep the rest of the day in view — “Change Sam's pull request review to 4 PM.” You can ask Foley to help plan your day around the tasks already there, follow the plan back to the work, and adjust it as you go. On mobile, the Plan tab answers questions like “What should I work on first?” from what is actually on your list. Clarification is a deliberate feature: when two tasks could fit what you said, Foley asks which one you mean. The approach that ties all of this together is voice plus verification. Capture is conversational, and the result is confirmed rather than assumed: after a capture the app shows what it saved, with the project and the time already set, and then it says so out loud — one sentence, by the same rules on every device — while the words stay on the screen whether or not the voice plays. When the voice does not play, the watch says why, in one dim line. History keeps your original words beside what Foley changed, so you can review the result and undo a capture when you need to. And because the phone, the desk and the browser share one list once you are signed in, a change made in one place is a change made everywhere. On the wrist, a short answer is read back before it goes anywhere, because that is where recognition is least reliable. The outcome Foley aims for is a lighter head and a clearer day. Tasks do not need to be remembered, because capture is only a sentence away on whatever device is nearest. Tasks do not need to be re-typed, because the project and the date arrive with them. Plans do not need to be rebuilt from scratch, because Foley plans around the tasks already on the list and you can adjust from there. And because the app asks rather than guesses, the list stays trustworthy — you are not silently filing tasks into the wrong project or accepting a wrong date. The Timeline groups what is late, what is due today and what the week holds across every project, so the day is one glance instead of a search. Concrete scenarios run through the whole product. In the middle of work, you press a shortcut and say “Add two tasks: buy milk, and call the electrician,” review the two tasks Foley produced, and carry on. Walking out of a meeting, you capture on your phone and Foley files it with the project and time already set. When something changes, you say “Change Sam's pull request review to 4 PM” and the day rearranges. When you are not sure where to start, you ask “What should I work on first?” and Foley answers from your list — for example, renewing an overdue parking permit before posting a parcel due at 12:30. On the wrist, a question like “Which area, and how many people?” can be answered with a tap on one of the suggested chips or by voice. And for a household errand, “Add bread to the shopping list” is enough. Foley is aimed at anyone who keeps a personal and professional task list and wants to keep it without doing the filing — knowledge workers at a desk, people who capture thoughts on the move, and anyone who wants their tasks on a watch as well as a screen. It runs on Mac and Windows desktop apps, in the browser at my.foleyapp.com, on iPhone and Android, and on Apple Watch (watchOS 10 or later) and Wear OS watches (Wear OS 3 or later). Setup lets you connect your tools, choose your capture shortcut, and decide which projects AI may use as context — and you can pick Foley-managed AI or bring your own key. Desktop task management is free, with no sign-in needed to get started and a personal AI key for AI features; your AI provider charges for personal-key usage. Foley Pro is $8 per month (currently $4 for the first month), with hosted AI without a personal key and your account across devices on monthly or annual billing. Website pricing may differ from store prices; signing in is required for hosted AI, sync and sharing. Foley's value proposition is that the thought is the work. By starting with voice — on a desktop shortcut, a phone, a browser tab or a watch — and finishing with a task that already has its project, date and reminder attached, it removes the administrative step that makes most task lists fail. It asks when it is unsure instead of guessing, it keeps your original words so changes can be undone, and it keeps one list in sync across Mac, Windows, web, iPhone, Android and the watches. The result is exactly what the product promises: out of your head, into your day.
Ayven describes itself as the AI super coordinator that carries and drives your team's agenda. It works on Slack and Microsoft Teams: she reads what is due, asks the one person who can move it, hands off what she cannot do herself, and follows every piece through to Done, with a ticket changing only on its owner's yes. In practice that means Ayven observes the work, cuts it into pieces the team can take one at a time, puts an owner and a date on each, and files them in Jira or YouTrack. From there she runs, tracks and talks about the work for weeks — asking whoever knows, waiting, chasing silence and moving work when someone is away. Your team answers in Slack and the board moves. Ayven is aimed at the people who own outcomes for a team: the leads, executives and founders whose initiatives stall because no single person is explicitly holding the next step. Every open question in new territory has no obvious owner, and the ones nobody owns are the ones that stall. That is the problem Ayven is built around. A ticket that gates a launch passes its due date and quietly sits there. A question asked at six dies in the thread until tomorrow, and nobody counts the day it cost. Three days with no next step is a stall. When you are finding out, what was true on Monday is wrong by Wednesday, and someone has to ask around. Worse, the few people who can push into the unknown are the ceiling, and every new initiative waits on them. Teams that staff this kind of work hire a chief of staff at a $160,000 median base, which is the coordination burden Ayven is designed to carry instead. Ayven's first job is driving and delegating the work itself. She observes what is happening, cuts it into pieces your team can take one at a time, puts an owner and a due date on each, and files them into the board your team already uses, such as Jira, YouTrack or Asana. What she cannot do herself becomes a ticket with an owner and a due date, filed after you approve it, and she follows it until the board says Done. When work runs late, she keeps it moving: past its due date she asks the assignee on the ticket, then hands the work to a teammate who can carry it once you say yes. She also moves work when someone is away. Throughout, she tells whoever raised the work as it moves, so the person who reported a problem hears about it the moment the ticket changes. Ayven also asks the person who actually holds each answer. She sends the question to whoever can answer it — one person by direct message, or the channel when anyone can. Before she asks, she reads the relevant ticket or document, so she is checking rather than guessing. She takes 'no reply yet' as an answer, asks another person when one goes quiet, and tells the asker who answered. One example on the site shows her checking billing and finding that the annual discount is applied at invoice time rather than at checkout, so the demo bug is in checkout, not pricing — she found the answer in the code and asked no one. Another shows her checking competitor prices before putting a pricing decision to a person, because the call gates the pricing page. A third capability is that Ayven reads the tools you already run rather than asking you to move into a new one. She reads Slack threads before writing, reads the live Google Drive doc, and re-reads Notion pages before she acts. She reads a ticket's state and due date in Asana, watches a Jira ticket through to Done, reads the due date off a YouTrack ticket, and reads a GitHub issue's state and owner. She reads the live SharePoint file and can browse any Microsoft Teams channel on demand. She asks through Slack and Microsoft Teams, checks the ticket or the doc before she asks, and files or reassigns on the board only after you approve the exact change. Ayven is built to work over time and in the background, over months. A promised Thursday is a deadline she keeps, no ask is left waiting forever, and she follows up in step with the deadline. On the site she works to a morning clock at 08:00, tracks expiry windows, and comments on a ticket the day it passes its date. For a goal such as a launch by a given date, she reads the due date off the ticket, notes a blocker, and acts — commenting on the ticket the morning after it passes, emailing you if the launch projects past its date, and recomputing after every step. The stated outcome is that she warns you about a slip while you can still do something about it, rather than after the fact. The centre of Ayven's approach is that her messages and comments go out on their own, but a change to a ticket waits for your yes. She files work she cannot do as a ticket once you approve it, reassigns only on your yes, and is watched to Done without ever marking a ticket Done herself. Missions hold multi-week work: you give the outcome, she messages the people each step waits on, comments on tickets past their date, and files or changes a ticket after you approve the exact change. A reply on the ticket or a move on the board updates the mission automatically, so the record stays true without anyone re-explaining it. The benefits follow directly from that model. Because Ayven carries the asking, the following-up and the coordination between people, those things happen on their own instead of waiting on a human to remember them. Planning stops being the barrier, and the team ships its agenda faster. More gets done with the same team, because the few people who can push into the unknown are no longer the bottleneck for every unrelated step. Responsibility stays clear — every piece has an owner and a date — and you are told when a ticket you care about moves, and when something you own slips, with enough time left to act. Concrete scenarios appear throughout the site. An account executive reports that two prospects hit the checkout bug in demos; Ayven files it as a ticket to an engineer, due Thursday, watches it until the board shows Done, and tells the account executive as it moves. A senior executive asks for a summer team trip to be organised; Ayven asks four people one question each — dates, venue, headcount and budget — in direct messages. A finance, product and sales update becomes one assembled draft on Google Drive, filed on the requester's yes, with each team asked for its own numbers by a Thursday noon deadline. Late work is chased on the ticket, then handed to a teammate once approved, and a launch-gating ticket past its due date triggers a comment on the ticket the same day. Ayven runs on Slack and Microsoft Teams and integrates with Google Drive, Notion, SharePoint, Asana, Jira, YouTrack and GitHub, so it reads the tools a team already runs rather than replacing them. Its stated audience is teams that would otherwise staff this coordination work by hiring a chief of staff, whose median base is $160,000. Pricing starts with a free plan at $0 that includes 500 credits a month, every integration included, and no card required; a 15-minute demo can also be booked. There is no mention of a separate paid tier on the site, though the credit-based free plan implies usage is metered. Taken together, Ayven is a coordinator rather than a dashboard: it takes the outcome you give it, asks the one person who can move each step, files and tracks tickets to Done, and keeps every change behind your approval. Its value proposition is that the asking, the chasing and the coordination stop depending on a human remembering them — the board moves, the record stays true, and you hear about a slip while you can still do something about it.
kōdlo is an AI-native sales workspace for high-ticket B2B teams. It finds prospects that fit your ICP, tells you how to warm each one up, and writes the message, the offer, and the deck from your own documents. Instead of stopping at a list, the workspace carries a deal through the full cycle: ICP interview, lead sourcing, list enrichment, deep research, cited brief, personalized outreach, pipeline update, campaign content, and closed deal. Your team tracks clients, contacts, and tasks in the same place, so nothing gets lost between steps. An agent sits on every page, and a shared memory layer means the research, outreach, and CRM capabilities never start from zero context. The product positions itself as the AI workspace for sales, built around one source of truth. Most sales tooling solves one slice of the cycle. As the site itself puts it, other sales tools hand you a list and stop. The gap is everything that comes after: understanding whether a prospect genuinely fits, finding the public signals that show how to approach them, writing outreach that sounds like you, and keeping the pipeline current while you do it. When each of those steps lives in a different tool, context fragments — the reasoning behind a lead, the sources behind a claim, and the history of a relationship all get scattered. kōdlo addresses this by holding your ICP, your contacts, your campaigns, and every brief the agent has written in one place, so prospects arrive with their signals and sources attached and stay that way. kōdlo's outbound loop starts with the ICP Builder, an interview-style setup where the agent builds your ideal customer profile with you. From there the Lead Discovery agent hunts for leads that match it, and each lead is backed by real signals rather than a guess. Those signals are drawn from public record sources the site lists explicitly: press releases, patent filings, job postings, trademark registries, conference programs, public funding rounds, open repositories, public LinkedIn pages, podcast transcripts, tender notices, Companies House, and SEC EDGAR. Every signal is cited to its source, so you can check for yourself that the fit is real. A list enrichment step sits between sourcing and research, filling out the records that discovery produces before the agent goes deeper on them. Deep research turns every account into a cited brief. The agent plans the question, runs the searches, cross-checks what it finds, and cites every source — on screen, step by step, while it happens. That visible trace (ask, plan, search, cross-check, cite) is what lets you see exactly where the agent went wrong when it is wrong. Research draws only on public sources, and every record carries the links it came from. The site notes that the record is live and re-indexed hourly, and that the lawful basis for processing is legitimate interest, documented. The result is a brief you can verify rather than a summary you have to trust, which matters a great deal when the account in question is a high-ticket deal where a wrong assumption is expensive. Outreach goes out personalized over LinkedIn or email and is drafted in your tone of voice. What makes it specific is the Knowledge Hub: you upload product catalogues and other documents, the hub parses them with OCR, and the agent turns them into personalized messages, offers, deep searches, and decks. The Knowledge Hub holds up to 1,000 pages on the Starter edition and up to 10,000 pages on Pro. On the closing side, pitch decks and proposals generate from your own template, so a deal that advances or closes turns into campaign content that keeps the account warm. Documents and attachments that arrive through the inbound lane are parsed and made queryable in the same workspace. The workspace pairs tools and agents on one shared context. On the tool side sit the capabilities your team works with every day: outreach, web intelligence, the Knowledge Hub, and CRM operations. On the agent side sit deep research, lead discovery, content and slide-deck generation, and scheduled automation jobs. Everything sits on a single memory layer made up of short-term memory, long-term session-wise memory, and user profiling memory, so no capability and no agent ever starts from zero context. The CRM and contact management keep the pipeline current, holding companies as an entity layer, people in each role, and the industry they move in. A ticket system handles inquiries, replies are grounded in Knowledge Hub citations and the memory of past threads, and Telegram and Google Chat connections deliver follow-ups and digests. Pro adds long-term session memory and agent learning. The stated outcome is continuity: each step feeds the next because they all run on the same data. Open a contact six weeks later, ask "what's next?", and the agent answers from the record it built — grounded in their public profile, their company news, and your own history with them. On the data side, the promise is that you pay for signal rather than seats: no per-contact charges and no data add-ons. Your data stays in your workspace, under GDPR, CCPA, and global privacy standards, with sourcing the site describes as GDPR-clean. Two workflows are described in detail on the site. In the outbound loop, you define the play with an ICP block, the Lead Discovery agent discovers leads, deep research qualifies prospects with cited briefs, and personalized LinkedIn and email outreach goes out in your tone of voice; the flow ends in a close-and-retain stage with pitch decks, proposals, and scheduled check-ins, and wins and losses feed back to refine the ICP. In the inbound lane, incoming inquiries become contacts and tickets with attachments parsed and queryable, every reply is grounded in Knowledge Hub citations and past threads, follow-ups and digests reach you in Telegram and Google Chat, and pitch decks and proposals generate from your own template. Closing and retaining run in the same workspace as the hunt. kōdlo is aimed at high-ticket B2B sales work: solo reps ready to work a real pipeline, small teams sharing one workspace, and organizations whose needs do not fit a standard plan. Pricing runs across three editions. A free tier offers a seven-day trial with one seat, the agent-native workspace, ICP Builder and Prospect Finder, integrated web and deep research, CRM and contact management, Knowledge Hub with OCR, cited deep research briefs, Telegram and Google Chat connection, and the ticket system. Starter is $49 per month plus VAT (about $43 per month on quarterly billing, a 15% saving) for one seat and Knowledge Hub OCR up to 1,000 pages. Pro is $199 per month plus VAT (about $169 per month quarterly) for up to three seats, workspace collaboration features, 4x month limits, long-term session memory, agent learning, and OCR up to 10,000 pages. An Enterprise edition adds custom AI agents built around your workflow, custom integrations, SSO and advanced security, SLA, DPA and procurement support, dedicated onboarding, and an optional bring-your-own-API-key option. Claude Desktop, ChatGPT Work, or your code agent can connect with kōdlo MCP to scale and orchestrate contexts. kōdlo's core proposition is an end-to-end sales workspace with unified context: one record that finds the prospect and answers the inquiry that arrives without one, one memory that every tool and agent shares, and one place where the ICP, the briefs, the outreach, and the pipeline live together. For high-ticket B2B teams, that means the research behind a lead is cited and checkable, the outreach is written from your own documents and in your voice, and nothing gets lost between the steps of the cycle.
Hypervibe is a native macOS application that brings AI coding agents together on one infinite visual board. Instead of juggling terminal tabs and separate windows, you can run Claude Code, Codex, Gemini CLI and a catalog of other command-line agents side by side as nodes on a single canvas. It is built for developers who already work with agentic CLIs and want to see, organize and orchestrate many of them at once, on their own Mac, using the agent subscriptions they already pay for. macOS 14 or later on Apple Silicon is required. The starting point for Hypervibe is a simple observation: don't let a screen decide how many agents you run. Developers adopting AI coding agents quickly hit the limits of the terminal. tmux gives you panes, but as the Hypervibe comparison puts it, it does not tell you which agent is waiting for you, hand a task from one agent to another, or bring every conversation back when you reopen. Terminal tabs multiply, context is lost between sessions, and there is nowhere to plan next to the work itself. Hypervibe keeps the real terminal and adds the board around it: status per console, teams, loops, voice, and a place to plan. Each console on the board is a real terminal. Every one is a full PTY with a controlling terminal, so Ctrl-C, job control and full-screen TUIs behave exactly like iTerm. The agents run as the interactive CLIs you are already logged into, which means you use your own subscription rather than API keys, and nothing falls outside the plan you already pay for. Hypervibe runs the binaries already on your PATH, supports Claude Code, Codex, Gemini, Grok, opencode and a catalog of 34 CLIs, and also accepts any custom executable you add yourself: if it runs in a terminal, it can live in a node. Around those terminals, Hypervibe provides a set of studios and board tools. Live web tiles show a localhost preview with a real Web Inspector docked to the board. A code studio lets you browse the file tree, preview code with highlighting, and pin files as nodes on the board. A markdown studio offers an Obsidian-style vault with a file tree, autosaving editor and a force-directed link graph. A diagram studio turns diagrams of your repo into loose ink figures you can spill onto the board and export as PNG or .excalidraw. A document studio generates documents from the repo with a live preview and exports a real paginated PDF. Kanban, sticky notes, text and checklists sit beside your consoles so you can plan next to the work, and ink and markup let you draw directly on the board or mark up dropped images in place. A live git card shows your branches alongside a GitHub panel for commit, push and pull. Orchestration is where the board goes beyond a pretty desktop. You can line up a whole team in the composer and launch twelve consoles in one action. Consoles can be grouped into teams, with a mission map to keep track, and work can be handed from one agent to another. Loops know when to stop: you can trigger a console on a schedule, on idle or on output, give the loop a goal, and it retires itself once the goal is met. Voice control lets you direct the board by speaking; the voice planner turns spoken instructions into plans and the app speaks short replies back. State and continuity are handled with care. Every workspace is saved on each change, and sessions come back so consoles return exactly where they were, conversation included. A usage pill per CLI and token analytics by day and agent are built from your local session logs. Profiles with isolated homes let you run two accounts of the same CLI side by side. Project memory works at the per-repo and global level, and nothing reaches a console unless you push it. Under the hood, Hypervibe is local-first. State lives on your disk as versioned JSON and speech is transcribed on-device. Only three things talk to the servers: your sign-in, handled by Firebase Authentication; your planner commands with their board context, which the planner service sends to Groq to turn into a plan; and the text of the short replies the app speaks, which the gateway sends to Inworld to generate audio. Your microphone audio and your repositories never leave your Mac. You also have the last word: agents type, but you send. Nothing prepared for you is ever sent for you, a live console only dies by an explicit confirmed action, and each CLI's auto-approval flag is a global opt-in that is off by default. Getting started follows three steps. First, install your CLIs: log in to Claude Code, Codex, Gemini or whichever agents you use, the same way you do today, and Hypervibe runs the binaries already on your PATH. Second, open a repo by pointing Hypervibe at a folder, which becomes a board with workspaces you switch like tabs and presets that lay one out in a single tap. Third, spawn consoles by adding agent consoles as nodes and putting them to work, directing them by voice or keyboard, grouping them into teams, or leaving them on a loop. The outcomes follow from that structure. Because every console is a real terminal, developer workflows, keyboard shortcuts and full-screen tools keep working. Because each agent runs on your own subscription, there is no resold model access and no separate API key bill. Because the workspace is saved on every change, reopening Hypervibe brings back the exact arrangement and conversations you left. Because loops can watch for output, idle time or a schedule, agents can keep working without a human watching each step, and because their goals retire the loops, automated work stops on its own. Concrete scenarios fall directly out of the features described. A developer can run Claude Code, Codex and Gemini CLI side by side on the same repo to compare their output, using profiles with isolated homes to run two accounts of the same CLI at once. A larger effort can be laid out as a team of consoles on a mission map, with handoffs between agents and twelve consoles launched at once from the composer. While agents work, you can keep a live localhost preview open in a web tile with the Web Inspector docked beside it, check the git card and push from the GitHub panel, or generate a PDF document and a repo diagram from the same board. Loops handle recurring or conditional work: a console triggered on a schedule, on idle or on output, given a goal like a specific task to finish, retires itself when the goal is met. Usage analytics track token consumption by day and by agent from local session logs. Hypervibe is for one person working on their own Macs. It requires macOS 14 or later on Apple Silicon, and ships as a direct download rather than through the Mac App Store because real terminals need to spawn real processes that the App Store sandbox does not allow. The Pro plan costs USD 19 per month, billed monthly with taxes calculated at checkout, and can be cancelled anytime with a 14-day refund window on first purchases and annual renewals. Pro includes 10,000 credits every month for the voice planner and spoken replies, unlimited on-device voice dictation, 34 agent CLIs on one visual board, teams, handoffs and automated loops, the documents, diagrams and code studios, and all updates. Credits renew monthly, and if they run out, new voice planner requests and spoken replies pause until renewal while the board, consoles, voice dictation and local commands keep working. Agent subscriptions such as Claude, Codex or Gemini are paid separately to their providers, and Paddle acts as merchant of record. A Discord community run by the makers of Hypervibe is open for showing boards, reporting bugs and shaping what comes next. The takeaway is that Hypervibe turns a pile of terminal tabs into one workspace for AI coding agents. It keeps the real PTY terminals and your existing subscriptions, then adds the board, the teams, the loops, the studios and the voice control that make running many agents at once manageable, all on your Mac and with your repos never leaving it.
Maildun for Mac is an agentic email builder for macOS, released as a free beta. It is part of the Maildun family of email tools: the open source Maildun platform, described on the website as the full email marketing stack for campaigns, sequences and transactional email; Maildun for Mac, a native Mac application for designing emails; and Maildun Platform, a managed version listed as coming soon with the promise "We run it, you send." The home page summarises the whole offering as "Campaigns, sequences, and transactional email. Run it yourself, design on your Mac, or let us host it for you." The Mac app is built for people who want to produce on-brand emails either by hand, with an AI assistant, or over MCP, and it is free to download. Maildun is positioned as email marketing tooling "built in the open." The open source edition is described as the full email marketing stack that you can self-host, read the code of, and help shape, and the site notes it is free to self-host. Rather than pushing teams toward a single closed hosted product, Maildun offers three ways to run the same idea: hosting it yourself, designing on your Mac, or letting the vendor host it for you through the forthcoming Maildun Platform. This matters because email remains a core channel for campaigns, automated sequences and transactional messages, and teams often want control over where their sending stack and their design workflow live. The Mac app gives designers a native place to build those emails, while the open source project and the upcoming managed platform offer a path to actually sending them. Designing by hand is the foundation of Maildun for Mac. The app provides a drag-and-drop editor in which you build an email by adding elements such as a heading and body text, as shown in the product's editor screenshot with the prompt "Write something people want to read." The editor exposes three views — Design, Preview and Code — so you can lay out the email visually, check how it will render, and inspect or edit the underlying code. An "Apply brand" action sits alongside the assistant and an export control in the toolbar. The result is a hands-on workflow in which the person designing the email keeps direct control over layout and copy rather than relying purely on generated output. The AI assistant takes that hand-built design and edits it live. Maildun for Mac lets you connect Claude, ChatGPT, Gemini or Grok using your own API key, so the model you already use can work directly on the email you are building. Critically, the assistant's changes are presented as a proposal that you accept or reject, rather than being applied silently to your design. That review step keeps a human in the loop: you can see what the assistant wants to change, approve it if it improves the email, or discard it and keep your original version. Bringing your own API key also means the choice of model provider stays with you, and the app supports several of the major assistants by name. Beyond the in-app assistant, Maildun for Mac ships with a built-in MCP server. Turning it on allows developer-facing AI coding tools — Claude Code, Codex and Cursor are the ones named — to create and edit emails as well. MCP, the Model Context Protocol, is the mechanism through which those tools talk to the app, and having the server built in means there is nothing extra to install beyond enabling it. This opens a second, more technical route into email production: instead of pointing and clicking in the editor, a developer or power user can ask an agent inside their coding environment to generate or adjust an email, with the resulting changes landing in the Mac app's design. Maildun for Mac also adds organisational features around the design itself. Workspaces per client let an agency or freelancer keep each client's emails separate, so one client's work does not bleed into another's. Brand kits carry shadcn-style component styles, and the "Apply brand" action brings those styles to a design, which helps keep every email visually consistent with the brand it represents. For repeatable layouts, saved sections let you store blocks you use often and drop them into new emails rather than rebuilding them each time. Media can be stored on your own Cloudflare R2 or Amazon S3 bucket, giving you control over where images and other assets live. And when an email is finished, it can be published to maildun.com. The overall approach is summed up in the Product Hunt tagline: "Design on-brand emails by hand, with AI, or over MCP." Maildun for Mac deliberately supports three ways of working on the same design rather than forcing a single path. You can build everything yourself in the drag-and-drop editor; you can hand an existing design to Claude, ChatGPT, Gemini or Grok and let the assistant propose edits; or you can enable the built-in MCP server and let Claude Code, Codex or Cursor create and edit emails through an agent. Whichever route you take, the app remains the place where the email lives, and the assistant's edits always arrive as proposals you accept or reject. Underneath, the wider Maildun project is open source and positioned as something you can self-host, read the code of, and help shape. The stated benefits follow from that mix of control and assistance. Because the Mac app is free and the open source platform is free to self-host, teams can adopt Maildun without a licence fee, and because the project is built in the open they can read the code and help shape it. Designing by hand keeps full control over the output, while the AI assistant speeds up changes without removing the designer from the loop — every suggestion is accepted or rejected rather than applied automatically. Support for MCP means the same email work can be driven from the AI coding tools many developers already use. Brand kits and saved sections reduce repeated work and help maintain consistency across emails, and media storage on your own R2 or S3 bucket keeps assets under your control. Concrete uses described in the material include building a marketing email by hand in the editor — adding a heading, writing body copy, and checking the result in Preview or Code view. Teams running campaigns, automated sequences and transactional email can use the wider Maildun stack for sending, with the open source edition self-hosted or the managed Maildun Platform used once it is available. Agencies and freelancers can organise work by client using workspaces and apply each client's brand kit so their emails look on-brand. Designers who want a faster first draft can ask the AI assistant to edit the design and then accept or reject its proposals. Developers can enable the MCP server and create or edit emails from Claude Code, Codex or Cursor, and finished emails can be published to maildun.com. Maildun for Mac is aimed at people who design emails — in-house marketers and designers, and agencies or freelancers working across multiple clients — as well as developers who want to generate emails from their coding tools. It runs on macOS as a native application and is free. The wider Maildun project is open source and free to self-host, with source code available on GitHub and a managed Maildun Platform listed as coming soon. Named integrations and connections include Claude, ChatGPT, Gemini and Grok for the AI assistant; Claude Code, Codex and Cursor through the built-in MCP server; Cloudflare R2 and Amazon S3 for media storage; and publishing to maildun.com. The Mac app is labelled beta, and Maildun itself is labelled open source beta. Maildun for Mac packages an on-brand email builder, a bring-your-own-key AI assistant and a built-in MCP server into a single free Mac app, and connects it to an open source email marketing stack you can self-host. Its core promise is choice: design by hand, with AI, or over MCP, while keeping the final say over every change.
Cue is a free macOS app that turns your headphones into a focus switch. Put your AirPods in and your Mac turns on your Focus mode, blocks distracting sites and starts a timer in the notch; take them out and it is break time, with your sites coming back. It runs on macOS 14 (Sonoma) or later and the download is built for Apple Silicon, and it is made for anyone who wants to start and stop focusing without opening yet another app. Most focus tools wait for you to open them, pick a mode and start a session manually. Cue takes the opposite approach: it starts when you put your headphones in and ends when you take them out, so there is nothing to remember. The problem it addresses is the friction between deciding to focus and actually being in a focused state: the small habits of opening an app, choosing a timer length and remembering to stop are exactly the moments where distraction creeps back in. Because triggering focus is tied to a physical action you already perform, putting earbuds in, the switch happens automatically and consistently. Cue also notes that macOS has no public way to set a Focus mode, so it sets up its own shortcuts once and switches Focus for you with no more prompts. The core of Cue is the link between your ears and your Mac. When AirPods are detected in your ears, your Focus mode turns on, distracting sites are blocked and the timer starts. The blocker covers social, video and news lists plus any sites you add yourself; you can paste a comma-separated list and Cue splits it. Apps you list are asked to quit while you focus. Both the blocked sites and the quit apps come back when you take a break. Take your AirPods out and, after a 10-second grace period in case you are only adjusting a bud, Focus turns off and your sites return. The break ends after 15 minutes by default, and you can set it anywhere from 5 to 60 minutes in Settings. AirPods Pro, Max, 3 and 4 are the most precise because they report when they are in your ears, but any Bluetooth headphones work, with other headphones starting the session when they connect. Cue lives in the notch: a small dot and a timer sit next to the camera cutout, and you point at it to open it, tap to pin it, and hover to see your day. There is no Dock icon and no window in the way. On Macs without a cutout, such as the MacBook Air M1, iMac, Mac mini and Mac Studio, Cue draws a floating 190 x 32 pill instead, and the same pill floats at the top of the screen when you are plugged into an external monitor. The notch serves as a compact surface for your session: now playing appears with artwork and play, next and previous controls for whatever is playing, from Spotify to a YouTube tab. Notifications from any app land in the notch instead of the corner and tuck away by themselves. Volume and brightness show in the notch rather than as a big box mid-screen. You can give the notch your own colors by picking from presets such as Peach, Lilac, Mint, Sunset and Aurora, or using Mix, which blends three to five colors you choose into three gradient options so you keep the one you like. Battery information appears when you open your AirPods case, showing each bud's battery with one-tap connect. Small islands cover extras such as keep awake, a caps lock indicator and a nudge to unplug at full charge, and a single switch hides the notch from recordings. Two tiny mascot buddies hang under the notch and react to what you do. They run while you focus, nap on your break, dance when music plays and blush when you point at them. New in version 2.6, outside a focus session the buddies leave the notch and roam your whole screen, walking on windows, climbing their sides, hanging from the menu bar and jumping between them. You can pick one up and throw it or click it to cheer. A loop button sprays 20 to 30 buddies out of the notch, and the power button adds ten more per tap up to 60; tap loop again and they all go home. The skin you pick is worn on screen too, with seventeen outfits free from day one and eleven dance moves that change with each phrase and stay smooth on the beat. The buddies also react to your music, volume, notifications, AirPods and face. When they are on the notch they bob to the volume level, cover their ears when it is loud and squint when it is bright. Cue says two roaming buddies cost no more than the notch alone. Cue's approach is built on three steps and one workaround. First, you put your headphones in and focus starts: your Focus mode turns on, sites get blocked and the timer starts. Second, you take them out and a break starts: after the 10-second grace period Focus turns off and your sites come back, with the break ending after a configurable 5 to 60 minutes. Third, you see your day: today against your goal, your streak and the last seven days all appear in one place. Because macOS provides no public way to set a Focus mode, Cue sets up its own shortcuts once and then switches Focus for you with no more prompts. The app is also deliberately private: there are no accounts and no analytics, and your data stays on your Mac. It sends only feedback you write yourself, an optional update check that is off by default, and two anonymous one-time setup signals (opened, ready). It is written in Swift only and is described as light as a feather. The result is a focus routine that starts with a physical habit rather than a decision. You do not have to remember to open an app or start a timer, and you do not have to remember to stop either, because taking your earbuds out ends the session and returns your blocked sites and quit apps. The notch keeps session information, media controls, notifications and system levels out of the middle of your screen, so nothing is in the way while you work. The optional Face Unlock, for Macs without Touch ID, lets the buddies look at the camera while Cue scans your face and wave a welcome back once you are unlocked; Cue itself notes this is for convenience, not security, since a photo of you could open it. Cue also greets you by name and reminds you to drink water and rest, and you can wear any of the seventeen free skins on the notch. Use cases follow the rhythm of a working day. When you sit down with earbuds in, Cue quietly starts a focus session, blocks the social, video and news sites you listed, quits the apps you asked to quit and begins the timer in the notch. While you work, the notch carries what is playing, incoming notifications and your session timer, so the middle of the screen stays clear. If you need to check something, you can take one bud out; the 10-second grace period covers the case where you are only adjusting, so a quick adjustment does not end the session, and then you settle back in. At break time, sites and apps return for the length you configured. At the end of the day you can open the Today tab to see minutes against your daily goal, your streak, your longest session, sessions today and the last seven days. Cue also supports other headphones: any Bluetooth headphones work and Cue tells them apart, with AirPods starting when in your ears and other headphones when connected. Cue is aimed at Mac users who want to reduce friction around focusing, particularly people who already wear AirPods or other Bluetooth headphones while they work. It requires macOS 14 (Sonoma) or later and the download is built for Apple Silicon. It is free: there are no ads, no accounts and no paid tiers, and all seventeen buddy outfits are free from day one. Installation involves downloading the DMG, dragging Cue to Applications and completing a one-screen setup; because Cue is a free hobby app and is not notarized by Apple (which requires a paid developer account), macOS asks you to confirm once through Privacy & Security before it opens. During setup you click Start, enter your password once for the site blocking helper, allow Motion, and turn Cue on in Privacy & Security to Accessibility; Full Disk Access is optional and lets you pick your own Focus modes. The app is written in Swift, and the maker describes it as vibe-coded by one person and Claude. A feedback form accepts feature requests, feedback, bug reports and notes, and an optional email list announces new versions. The site is available in English and Vietnamese. In short, Cue turns a pair of headphones into the simplest possible focus switch for the Mac: in means focus, out means break, with site blocking, a notch timer, media and system controls, playful mascots and a private, account-free design. For anyone who wants focus to start on its own rather than from an app they have to remember to open, Cue makes the transition automatic and keeps everything it needs to show you in the notch.
Onepin is an AI voice production agent that turns any script into voice that is ready to ship — model-matched, validated, and auto-fixed. It sits on top of the text-to-speech models teams already use, handling the models, the cleanup, the pronunciations, and the checks so that every line comes out production-ready. The site describes its role simply: text-to-speech creates voice, and Onepin decides what ships. It is built for teams shipping AI voiceover in several languages, including product videos, dubbing, and courses, and it is free to start with no credit card required. Onepin exists because of a specific gap in modern voice AI. AI voices sound human now, but they still guess names from the spelling, and nobody has time to listen to every line. Addresses, prices, dates, and abbreviations make every TTS model stumble, and mispronouncing a brand, a drug, or a name can make an entire line unusable — it is the first thing generic TTS gets wrong. One wrong name ruins the take. Onepin attacks these failures on both sides of synthesis so that teams producing multilingual voice work do not have to catch every error by ear or listen to each take twice. The first pillar of Onepin is access to every top text-to-speech model in one place. A script flows into 30+ models behind one account, routed line by line. Named providers shown on the site include ElevenLabs, OpenAI, Google, Microsoft, AWS, Cartesia, Murf AI, Deepgram, MiniMax, Inworld, Rime, Fish Audio, and Naver Clova, with more than twenty additional models listed. Because no model wins every language, Onepin benchmarks continuously and picks per run, so the model choice is made for each job instead of being fixed up front. That has a practical operational value: if a provider hikes prices, deprecates a capability, or shuts down, the pipeline does not move. Teams shipping at scale never have to marry one model again, which matters most when the output is going out to customers and legal teams alike. The pipeline then starts by cleaning the text before a single line is generated. Addresses, prices, dates, and abbreviations — described as the most common cause of misreads — are normalized in every language before synthesis, so the model pronounces the script the way it was meant. The site illustrates this with strings such as 3042 becoming thirty forty-two, St. resolved as either Saint or Street depending on context, and NW expanded to NorthWest. Because these cases are fixed before synthesis rather than after, roughly half of voice errors are removed up front, which means fewer regenerations, fewer review cycles, and far less manual correction for anyone producing voice at volume. Pronunciation is the next stage, and it is treated as the highest-stakes one. Onepin uses a 4M word dictionary that teaches how to say the hard words right, in any language. It covers brand and product names, complex medical and drug terms, and hard names in any language. The examples on the site span consumer brands and artists — AbbVie, Versace, Sade, Siobhán, Måneskin, Hermès, Givenchy, Björk, Saoirse, Stromae, Balenciaga, Rammstein, Röyksopp, Moët, Ng, Xóchitl, and Hoegaarden — alongside medical and scientific terms such as semaglutide, esomeprazole, hydroxychloroquine, esophagogastroduodenoscopy, and electroencephalography, each paired with a phonetic transcription. The point is that a single mispronounced name or drug term forces a redo of the whole line, so getting pronunciation right is the difference between a usable take and a wasted one. After generation comes validation. Every line comes back scored on four dimensions: naturalness, word accuracy, clarity, and pronunciation. The same bar is applied in every language, and lines are scored against your bar rather than the provider's, so one standard holds across an entire multilingual project. The site shows this working across locales — a US line, a Spanish line, a Japanese line, a Korean line, and a German line — each returning with its own score. That means a team can review a project by looking at scores instead of listening line by line, and can spot which specific lines need attention before anything ships. The final stage is automatic repair. Misses fix themselves: when a line is flagged, Onepin either regenerates the line or fixes just the word that missed. The example given is a line where Siobhan was misread — the system holds the gate on that line and corrects it, using the same model with new settings, without re-rendering the entire take. The stated outcome is that you always get the best take. Because only the failing word or line is touched, the rest of the approved audio is preserved, which keeps a review workflow from cascading into a full re-record. Overall the method is a single drop-in workflow: you drop in your script, and Onepin handles the models, the cleanup, the pronunciations, and the checks. The site frames it as a three-part flow on screen — select, generate, validate — backed by four pipeline steps: clean, pronounce, validate, and fix. The promise is a script that goes in and production-ready lines that come out, on the voices you already use, without a person having to listen to every line twice. The benefits extend beyond audio quality into how a team operates. Because output quality is scored rather than guessed at, review becomes a matter of checking scores and fixing flagged lines. Because model routing is abstracted, procurement risk is reduced. The site also addresses ownership directly: every output is assigned to you and cleared for commercial use, and Enterprise adds a negotiated IP indemnity, so the audio can legally ship. On the cost side, you buy one credit volume and allocate it across workspaces, reallocating anytime, with seats provided free — a structure designed for multiple teams drawing from a single pool. Use cases named on the site include product videos, dubbing, and courses for teams shipping AI voiceover in several languages, and the demo script panel offers verticals such as Product, L&D, Healthcare, Support, Travel, and Sports. The site also illustrates the kinds of lines where pronunciation decides the outcome: a gaming line — Slough off the poison before it spreads; an audiobook line about the minute inscription above Hawthorne's tomb; an advertising line about booking a stay in Yosemite before the summer rush; an e-learning line about the reign of Louis XIV; and a film line about subtlety never being his forte. Each depends on a name, a number, or a word that generic text-to-speech tends to get wrong. The product also states it is trusted by teams shipping voice at scale, listing HeyGen, Hyundai Motor Group, Sierra, Bland, and Johns Hopkins University. On integrations and commercial terms, Onepin connects to the voice providers it routes across, including ElevenLabs, OpenAI, Google, Microsoft, AWS, Cartesia, Murf AI, Deepgram, MiniMax, Inworld, Rime, Fish Audio, and Naver Clova, with more than twenty additional models reachable through the same account. Access starts free with no credit card required, and the pricing section positions Pro for when you are shipping, with a contact option for larger needs. Enterprise adds the negotiated IP indemnity mentioned above. In short, Onepin is the production layer between your script and shippable voice: it cleans the text, gets the names right, scores every line, and fixes the misses automatically across 30+ TTS models in any language. Its core value proposition is confidence — shipping AI voice you do not have to listen to twice.
Phonable is smarter voicemail for iPhone. When you cannot pick up, callers hear your greeting and get a text back; if they leave a message, you get a transcript and an AI summary within seconds. It is built for iPhone owners who are not always able to answer the phone, whether they are in a meeting, on the road, mid-workout or away for the weekend, and it works alongside your existing number rather than replacing it. You keep your own number, no new SIM is needed, and the service is free to start, so the product's main purpose is to handle the calls you miss on both ends of the conversation. Phonable exists because a missed call leaves both sides hanging. As the product describes it, carrier voicemail has not changed in decades: a beep, a message you never get round to, and a caller left wondering. Phonable takes care of both ends of the call. Instead of a caller being greeted by a generic carrier beep and never knowing whether their message was received, Phonable speaks to them with a greeting you chose and follows up with a text, while you receive the message already transcribed and summarised. The result is that nobody is left guessing what happened after a call went unanswered. Text back, so callers are never left guessing. The moment you miss a call, Phonable sends a short text on your behalf, even when the caller hangs up without leaving a voicemail. Templates include "In a meeting", "Driving" and "Back on Monday", or you can write your own. The system is considerate by default: each caller receives at most one text per hour, so someone who tries twice is not flooded with messages. Because each mode has its own text, what callers read always fits where you are, whether that is driving, at the gym or away for the weekend. Texts use the SMS credits in your plan and are not sent to landlines or to countries that Phonable does not support yet. Visual voicemail, summarised. There is no more dialling in and pressing 1. Every voicemail appears in the app with the recording, a full transcript and a one-line AI summary, so you know what the message is about in seconds. The AI summary arrives as a notification before you have even opened the app. You can skim the transcript or listen to the recording at the speed you like, and reply in one tap by calling back or sending a message straight from the voicemail. Greetings that sound just right. If you are not a fan of recording yourself, you can type what you would like to say, pick a voice and a tone, and Phonable speaks it naturally; if you prefer your own voice, you can record it in seconds. The listed AI voices are Sarah (soft and reassuring, American), George (warm and trustworthy, British), Laura (bright and upbeat, American), Lily (clear and polished, British), Brian (deep and composed, American) and Charlie (casual and friendly, Australian). Any of those voices can be used in any tone: Professional, Friendly, Calm or Energetic. Modes are new in 2.0 and give you one tap for every situation. A mode pairs what callers hear with the text they get back. You can switch from Workday to Driving in one tap, keep a mode on for a while (an hour, three hours or until tomorrow morning), or let it switch on by itself with a schedule that picks the days and hours. The modes shown include Workday ("Sorry I missed your call. I'm in a meeting and will call you back within the hour."), Driving ("I'm driving right now and can't pick up. I'll get back to you as soon as I've parked."), Gym ("Mid-workout, can't pick up! I'll call you back within the hour.") and Weekend ("Thanks for calling! I'm away until Monday. For anything urgent, send me an email."). Modes and scheduled switching are available on the Basic and Pro plans. How it works: Phonable uses conditional call forwarding, a standard feature of mobile networks. You keep your number, your SIM and your phone, and Phonable only steps in when you do not answer. The flow has four steps. First, you miss a call, in a meeting, on the road or out of signal, and the calls you do not take are forwarded to your Phonable line. Second, the caller hears your greeting, either your own recording or a natural AI voice reading the words you typed. Third, the caller gets a text back telling them why you could not pick up and when you will get back to them. Fourth, you get the gist, with any voicemail transcribed and summarised and the summary landing in your notifications. Forwarding covers three situations: when you do not answer (it rang out while you were busy), when you are busy (you are already on a call, or you tap decline) and when you are unreachable (flight mode, a flat battery or no signal). Setup shows you exactly what to dial and walks you through three quick steps that take about a minute, and you can switch back anytime. When you do answer, nothing changes: the call connects as usual and Phonable is not involved. The little things are done well too. Every call appears at a glance in one timeline, by name, and if someone hung up without leaving a message you can still see that they got your text. Callers show up with the name from your contacts rather than a bare number. Phonable is private by design: your contacts stay on your iPhone and are never uploaded, and the company states that it never sells your data. You can upgrade to a dedicated Phonable line that only handles your calls, and the app has a calm design that follows your iPhone's light and dark mode. The benefits and outcomes are straightforward. The core promise is that you stop leaving callers hanging and you stop dialling into voicemail to find out what was said. Callers know you got the call and what happens next, and you know what a message is about in seconds, with the gist delivered to your notifications before you open the app. Replying takes one tap, so returning a call or sending a message happens straight from the voicemail. Because texts are limited to one per caller per hour, the automatic follow-up stays considerate rather than spammy. Typical use cases map directly onto the modes. In a meeting, Workday mode tells callers you are in a meeting and will call them back within the hour. On the road, Driving mode explains that you are driving and cannot pick up and that you will reply once you have parked. Mid-workout, Gym mode says you cannot pick up and will call back within the hour. Away for the weekend, Weekend mode tells callers you are away until Monday and suggests email for anything urgent. When you are unreachable, whether through flight mode, a flat battery or no signal, conditional call forwarding still sends the call to Phonable, and when you are already on a call or tap decline, the caller still receives a greeting and a text. Plans and availability. Phonable offers Test Drive, a free plan that includes greetings, voicemail and text backs, a monthly allowance of voicemails and texts, up to two modes and a shared community line. Basic, billed monthly or yearly, is for everyday use with more voicemails and texts every month, up to five modes and modes that switch on a schedule. Pro, also monthly or yearly and marked most popular, includes the most voicemails and texts, unlimited modes on a schedule, AI voice greetings and a dedicated line that is only yours. Prices are shown in the App Store in your local currency, yearly billing saves 20% and you can cancel anytime in your App Store settings. Phonable is available as an iPhone app through the App Store. Phonable takes the awkwardness out of the missed call: callers get an answer and a text immediately, while you get transcribed, AI-summarised voicemails in your notifications, all without changing your number. Missed calls, handled.