# Whisperer

> Whisperer is an intelligent AI platform (AI Workspace) that brings together people, their knowledge,
> meetings, documents, tasks, calendars, communications and artificial intelligence into a single, unified
> ecosystem. It helps users capture and preserve knowledge, understand information, automate repetitive
> workflows, and work more efficiently with the power of modern AI models. Whisperer runs as a web app and as
> native macOS and Windows clients, with an interface available in 16 languages.

Whisperer is designed as a Swiss Army knife for productivity: every new capability is not a separate product,
but another blade of the same tool. Every feature is deeply integrated, shares the user's context, strengthens
the rest of the platform, and works as part of one cohesive system rather than as an isolated module.

- Listens: live transcription of microphone and system audio, with speaker labels and timestamps.
- Suggests: real-time answers in a desktop overlay that stays invisible in screen sharing; every suggestion is built from the running transcript, your knowledge base and your profile, not from one isolated question.
- Searches your own knowledge: notes with wiki-links and a knowledge graph; retrieval-augmented generation (RAG) mixes them into every answer.
- Sees: analyses screenshots and what is on screen — diagrams, charts, slides, code, terminal errors.
- Translates: live translation — the other side speaks their language, you read yours as the call runs.
- Adapts: a model chosen per role and per task across OpenAI, Anthropic, Google, DeepSeek, Qwen, Moonshot, xAI and NVIDIA, on one subscription.
- Runs your own prompts: you write the prompt, attach skills, pick the model and the context each answer role uses.
- Documents: turns the transcript into structured notes and action items.
- Summarises: a mind map of decisions and analytics after the call, with export to Markdown, SRT, VTT and JSON.
- Calendar and video rooms: a room lives inside the event, guests join by link; two-way sync with Google Calendar, Outlook and CalDAV.
- Tasks: decisions from a call become cards on a kanban board with due dates, priorities and labels.
- Files: folders, search and drag-and-drop upload; room recordings land there and become a meeting with a transcript.
- Connects: Notion, Slack, HubSpot and Zapier in your account, plus an MCP server that lets Claude, ChatGPT and Cursor read and act on your Whisperer data.
- Acts: Leo, the built-in AI agent, sees your meetings, tasks, calendar and files and acts in the same places.
- Writes code: a dedicated coding role that runs on its own model, chosen independently of the rest.
- Works through system design: a structured answer format with component diagrams and the reasoning behind each decision.
- Works on any call: Zoom, Google Meet, Microsoft Teams, Telegram, Discord and others — without bots, plugins or per-service integrations.

The mission of Whisperer is to help people work smarter with information, automate routine tasks, and
transform data into knowledge through the power of artificial intelligence.

## Machine-readable layer

- [Full corpus](https://whisperer.one/llms-full.txt): every document below plus the whole English documentation, in one file
- [Product overview](https://whisperer.one/llms/product.md): what Whisperer is, which category it belongs to, and what it is not
- [Concepts and vocabulary](https://whisperer.one/llms/concepts.md): strict definitions of Whisperer entities and how they differ from each other
- [Capabilities](https://whisperer.one/llms/features.md): the full capability set with links to documentation
- [Leo, the AI agent](https://whisperer.one/llms/agent.md): what the built-in agent can do and the boundaries it never crosses
- [Meetings](https://whisperer.one/llms/meetings.md): how a call is captured, what happens during it and what it becomes afterwards
- [Hubs](https://whisperer.one/llms/hubs.md): the place a body of work lives, and how a meeting finds its own
- [Tracker](https://whisperer.one/llms/tracker.md): the kanban board, and where tasks come from
- [Memory](https://whisperer.one/llms/memory.md): the agent's long-term memory, and how it differs from the knowledge base
- [Knowledge base](https://whisperer.one/llms/knowledge.md): notes, documents, the knowledge graph and retrieval into answers
- [File storage](https://whisperer.one/llms/files.md): folders and files, and the boundary with the knowledge base
- [Workflows](https://whisperer.one/llms/workflows.md): the real end-to-end flows: after a meeting, before a meeting, during a call
- [Integrations](https://whisperer.one/llms/integrations.md): calendars, connected services, MCP in both directions, and export
- [Programmatic access](https://whisperer.one/llms/api.md): what is public, what is not, and which endpoints are safe to build against
- [MCP server](https://whisperer.one/llms/mcp.md): endpoint, discovery, scopes, exposed tools and limits
- [Plans and pricing](https://whisperer.one/llms/pricing.md): the four plans, what each unlocks, and what unlimited minutes means
- [Security and data boundaries](https://whisperer.one/llms/security.md): what is stored, what is never exposed, and how access is authenticated
- [Frequently asked questions](https://whisperer.one/llms/faq.md): the canonical short answers about Whisperer
- [Category and positioning](https://whisperer.one/llms/competitors.md): which category Whisperer belongs to and which it is mistaken for

## Product

- [Whisperer (Russian)](https://whisperer.one/): product overview, features, pricing, and FAQ
- [Whisperer (English)](https://whisperer.one/en/): product overview, features, pricing, and FAQ
- [Pricing](https://whisperer.one/#pricing): subscription plans and limits

## Documentation

- [Whisperer Docs](https://whisperer.one/docs/en/): product documentation, setup guides, and troubleshooting
- [What is Whisperer](https://whisperer.one/docs/en/getting-started/what-is-whisperer.md): Whisperer is an intelligent AI platform (AI Workspace) that brings knowledge, meetings, documents, tasks, calendar and AI models into a single ecosystem: they share one context,…
- [Quickstart in 5 minutes](https://whisperer.one/docs/en/getting-started/quickstart.md): This page walks you through the full path: from creating an account to your first working session in the overlay.
- [Your first session: step by step](https://whisperer.one/docs/en/getting-started/first-session.md): A session is a single listening run of a call: Whisperer listens to the audio, keeps a transcript, and answers your questions.
- [System requirements and platforms](https://whisperer.one/docs/en/getting-started/system-requirements.md): Whisperer has two parts: a native desktop client and a web dashboard.
- [Glossary of key entities](https://whisperer.one/docs/en/concepts/glossary.md): This glossary collects definitions of Whisperer's core concepts — from the call session to the knowledge base and plans.
- [What Leo remembers](https://whisperer.one/docs/en/concepts/leo-memory.md): Memory is Leo's long-term memory of you, kept between sessions: stable facts, preferences and how recurring things are usually done.
- [Subscriptions, plans, and quotas](https://whisperer.one/docs/en/concepts/subscriptions-and-quotas.md): Your subscription determines what's available to you in Whisperer: how many recognition minutes you can use, whether the knowledge base is open, and whether you can choose the…
- [Session Lifecycle](https://whisperer.one/docs/en/concepts/session-lifecycle.md): A session is the core unit of work in Whisperer: the time window during which the client listens to a meeting, transcribes speech, and receives LLM responses.
- [Transcript and Speakers](https://whisperer.one/docs/en/concepts/transcript-and-speakers.md): Whisperer transcribes speech in real time using Whisper — OpenAI's multilingual model.
- [Model Roles and LLM Access](https://whisperer.one/docs/en/concepts/model-roles.md): Whisperer uses several specialized models through a unified AI gateway — one per task.
- [No-Logs Mode (Ephemeral Mode)](https://whisperer.one/docs/en/concepts/no-logs-mode.md): No-logs mode is a privacy toggle that prevents Whisperer from saving the transcript and LLM responses after a session ends.
- [Knowledge Base](https://whisperer.one/docs/en/concepts/knowledge-base.md): The knowledge base is your personal note store that Whisperer automatically connects to LLM responses in real time.
- [User Context](https://whisperer.one/docs/en/concepts/user-context.md): User context is background information about you that you set once in the dashboard.
- [Model Catalog and Plan Availability](https://whisperer.one/docs/en/concepts/model-catalog.md): Whisperer uses different AI models for different tasks.
- [Knowledge Graph (Wiki-links)](https://whisperer.one/docs/en/concepts/knowledge-graph.md): The knowledge graph is a visual map of the connections between notes in your knowledge base.
- [Registration and e-mail confirmation](https://whisperer.one/docs/en/account/registration.md): A Whisperer account is a single login for both the web dashboard and the macOS client.
- [Pairing the desktop client with your account](https://whisperer.one/docs/en/account/desktop-pairing.md): For the Whisperer macOS client to work with your sessions, subscription, and knowledge base, you need to pair it with your account once.
- [Installing the macOS client and updating](https://whisperer.one/docs/en/macos-client/install.md): The Whisperer macOS client is a desktop overlay that listens to your call audio, keeps a live transcript, and suggests replies right on top of any video service (Zoom, Google…
- [macOS permissions](https://whisperer.one/docs/en/macos-client/permissions.md): For Whisperer to hear the call, respond to hotkeys, and read screenshots, it needs three macOS system permissions: Microphone, Screen Recording, and Accessibility.
- [Installing the Windows client](https://whisperer.one/docs/en/windows-client/install.md): The Whisperer Windows client is a native Windows app that listens to your call audio, keeps a live transcript, and suggests replies right on top of any video service (Zoom, Google…
- [Windows permissions](https://whisperer.one/docs/en/windows-client/permissions.md): The main difference between the Windows client and the macOS one: the only permission that requires user action is microphone access.
- [Leo, the AI agent](https://whisperer.one/docs/en/features/leo-agent.md): Leo is the AI agent built into Whisperer.
- [Hubs: where a body of work lives](https://whisperer.one/docs/en/features/hubs.md): A hub is the place a body of work lives — a client, a project, a hiring round, a release: "Acme — rollout", "Hiring a designer", "Release 2.0".
- [Task tracker](https://whisperer.one/docs/en/features/tracker.md): The tracker is the kanban board inside Whisperer.
- [Live transcription](https://whisperer.one/docs/en/features/live-transcription.md): Live transcription is a real-time transcript of your call.
- [Real-time AI suggestions](https://whisperer.one/docs/en/features/ai-suggestions.md): AI suggestions are answers that Whisperer generates right during a call, based on the live transcript, your questions, and your knowledge base.
- [Real-Time Translation](https://whisperer.one/docs/en/features/realtime-translation.md): Whisperer translates meeting participants' speech in real time and shows the translation directly in the overlay — without switching windows and without delay.
- [Screenshots and Vision (Image Analysis)](https://whisperer.one/docs/en/features/screenshots-and-vision.md): Whisperer can take a screenshot during a meeting and instantly analyze it with AI.
- [System Design Mode](https://whisperer.one/docs/en/features/system-design-mode.md): System Design Mode is a special Whisperer response format optimized for architectural questions: it delivers structured answers with text diagrams, component schemas, and…
- [Mind-Map and Meeting Analytics](https://whisperer.one/docs/en/features/mindmap-and-analytics.md): After each session, Whisperer automatically analyses the transcript and builds a structured meeting map — a mind-map.
- [Session History and Export](https://whisperer.one/docs/en/features/history-and-export.md): All completed meetings are saved in the dashboard: full transcript, AI responses, and the mind-map.
- [Prompt Studio](https://whisperer.one/docs/en/features/prompt-studio.md): Prompt Studio is the section of the web dashboard where you configure personal templates for AI responses.
- [Supported video services](https://whisperer.one/docs/en/integrations/supported-services.md): Whisperer supports any video service — Zoom, Google Meet, Microsoft Teams, Telegram, Discord, and others.
- [MCP: connecting Claude, ChatGPT and Cursor](https://whisperer.one/docs/en/integrations/mcp.md): MCP (Model Context Protocol) is an open standard that lets an external AI client work with your data in another service.
- [Programmatic access and automation](https://whisperer.one/docs/en/integrations/api.md): There are three ways to work with Whisperer without using the interface: the MCP server for AI clients, connected services for routine automation, and export for moving material…
- [Plans and what's included](https://whisperer.one/docs/en/billing/plans.md): Whisperer offers four plans: the free Free and the paid Start, Pro, and Max.
- [Limits and quotas](https://whisperer.one/docs/en/billing/limits-and-quotas.md): Whisperer's main limit is transcription minutes.
- [Payment: currencies, methods, promo codes, referrals](https://whisperer.one/docs/en/billing/payment.md): This page describes how Whisperer subscription payment works: which currency you pay in, by which methods, and how promo codes, the referral program, and refunds work.
- [Promo Codes and Referral Program](https://whisperer.one/docs/en/billing/promo-codes-and-referrals.md): Whisperer supports two ways to save on your subscription: promo codes with a discount or bonus days, and a referral program through which you earn a reward for every friend you…
- [Subscription Cancellation and Refund](https://whisperer.one/docs/en/billing/cancellation-and-refund.md): This article explains how to end your subscription, what happens to your access after it expires, and how to request a refund.
- [Data security and privacy](https://whisperer.one/docs/en/security/data-and-privacy.md): Whisperer listens to your calls, so we take a conservative approach to your data: we store only what's needed for history and search, we offer a mode in which nothing is saved,…
- [Can't hear the other person or the microphone](https://whisperer.one/docs/en/troubleshooting/audio.md): Whisperer listens to a call from two sources: your voice — through the microphone, the other person's voice — through system audio.
- [macOS permission problems](https://whisperer.one/docs/en/troubleshooting/macos-permissions.md): Sometimes a macOS permission is granted (the toggle is on), but Whisperer still behaves as if it isn't: you can't hear the other person, hotkeys don't fire, screenshots aren't…
- [Troubleshooting: Connection Issues](https://whisperer.one/docs/en/troubleshooting/connection.md): Whisperer maintains a persistent connection to the server during a session.
- [Troubleshooting: Login and Confirmation Code Issues](https://whisperer.one/docs/en/troubleshooting/login.md): This article will help you resolve common difficulties when registering, signing into your account, and confirming your email: the confirmation email does not arrive, the code has…
- [Troubleshooting: Payment Issues](https://whisperer.one/docs/en/troubleshooting/payment.md): This article covers common situations when paying for a subscription: payment failed, subscription did not activate, wrong amount, how to request a refund.
- [Troubleshooting: Minute Limit Reached](https://whisperer.one/docs/en/troubleshooting/minute-limit.md): Whisperer counts the actual time audio is recorded.
- [Whisperer for Job Interviews](https://whisperer.one/docs/en/use-cases/interview.md): Whisperer is your personal assistant that listens to the interview in real time, suggests answer structures, expands examples, and helps with technical questions — all invisible…
- [Whisperer for Sales and Negotiations](https://whisperer.one/docs/en/use-cases/sales.md): Whisperer helps sales managers and negotiators: it tracks the flow of the conversation, suggests counter-arguments for objections, prepares answers to product questions, and…
- [Best Practices for Using Whisperer](https://whisperer.one/docs/en/use-cases/best-practices.md): The tips here are distilled from what actually works for Whisperer users.
- [Frequently asked questions (FAQ)](https://whisperer.one/docs/en/faq.md): Here are short answers to the most common questions about Whisperer — from privacy on a call to billing and choosing a model.

## Articles

- [Whisperer Blog](https://whisperer.one/en/blog/): guides on running meetings, minutes and interviews
- [Daily standup: how to run one that doesn't turn into a ritual](https://whisperer.one/en/blog/daily-standup/): What a daily standup is and how it differs from a meeting: four formats with timing, a ready list of questions and what to capture so the time is not wasted.
- [How to run a meeting that ends in decisions, not in talk](https://whisperer.one/en/blog/how-to-run-a-meeting/): How to run meetings that end in decisions: preparation, who to invite, roles and timing, handling disagreement, the record afterwards and four antipatterns.
- [System design interview: how the session actually works](https://whisperer.one/en/blog/system-design-interview/): What a system design interview actually measures: a seven-step answer framework with timing, questions to ask first, four classic problems and where candidates fail.
- [Internal knowledge base: how to build one people actually use](https://whisperer.one/en/blog/internal-knowledge-base/): An internal knowledge base answers “how we do things here and why”. What belongs in it, why a structure by department falls apart, and how to launch one in a week.
- [Meeting summary: what belongs in it and how to get one](https://whisperer.one/en/blog/meeting-summary/): What a meeting summary is, how it differs from minutes, a ready template and the follow-up email — plus what to do when the built-in summary never arrives.
- [AI in interviews: where help ends and cheating begins](https://whisperer.one/en/blog/ai-in-interviews/): Real-time prompts, an overlay invisible on screen share, and the line where help turns into deception. How the mechanism actually works, what really gives a candidate away, and where AI belongs.
- [A live interpreter for Zoom, Google Meet and calls: speak your own language](https://whisperer.one/en/blog/live-translation-zoom-meet/): Real-time conversation translation: why latency matters more than vocabulary, how to speak your own language on any call — and where the limits are.
- [An AI interview assistant: prompts during the interview and a broken hiring market](https://whisperer.one/en/blog/ai-interview-assistant/): What AI can do before, during and after an interview, where help turns into substitution, and why interviews are a poor measuring instrument. No moralising.
- [An AI assistant for developer meetings: code, tasks and decisions that survive](https://whisperer.one/en/blog/ai-for-developer-meetings/): Three things were decided in the meeting; two days later nobody remembers the second. Why a transcript isn't enough and how a decision reaches a task with its reason intact.
- [AI lecture notes: turning a recording of a class into notes you can study from](https://whisperer.one/en/blog/ai-lecture-notes/): A transcript is not yet a set of notes. The seven blocks that make it study material, how a recording becomes structure, and what still remains your own work.
- [From a recording to minutes that work: decisions, tasks and commitments](https://whisperer.one/en/blog/meeting-minutes-from-recording/): A transcript, a summary, minutes and an outcome are four different things. How to get six working blocks out of a recording — and why owners and deadlines still need a human eye.
- [AI finds the tasks and commitments after a meeting — nothing gets lost](https://whisperer.one/en/blog/meeting-action-items/): The path from «agreed» to «done» breaks in six places. What a machine can find in a conversation, what it must not decide for you, and why a recording alone is not enough.
- [AI meeting assistant: what it is, how it works and why you need one](https://whisperer.one/en/blog/ai-meeting-assistant/): How it differs from a recorder and a transcriber, how the pipeline from audio to tasks works, where it fails, and why you need one when ChatGPT exists.
- [Whisperer vs Otter: why a transcript isn't the finish line](https://whisperer.one/en/blog/whisperer-vs-otter/): Otter turns a call into good notes. Whisperer helps inside the call — a prompt in an overlay, live translation across 16 languages — and turns a promise into a task with a deadline and a source. Compared against primary sources.
- [Whisperer vs Granola: notepad or workspace](https://whisperer.one/en/blog/whisperer-vs-granola/): Granola carries a conversation to an excellent document; Whisperer carries it to tracked work. An honest, source-checked comparison: transcription, memory, MCP, privacy, pricing — and where Granola simply wins
- [Why AI forgets, and how memory works in Whisperer](https://whisperer.one/en/blog/why-ai-forgets/): A context window is working memory, not storage. The engineering problem in full: entry kinds, half-lives, dedup, retrieval budget, and what we deliberately never record.
- [Meet Leo, the AI agent](https://whisperer.one/en/blog/ai-agent-that-takes-action/): Leo is the AI agent inside Whisperer: it sees your meetings, tasks and calendar, and acts in the same places. 107 tools, commitments extracted from meetings with a source, and boundaries no setting removes.
- [Meeting notes without a bot: three mechanisms and what each one cannot do](https://whisperer.one/en/blog/meeting-notes-without-bot/): A browser extension, an official platform API and OS audio capture. How each works, what it fails to give you, and which to pick — including the price nobody states.
- [How to connect your meetings to Claude Desktop and Cursor over MCP](https://whisperer.one/en/blog/meetings-mcp-claude-cursor/): MCP gives an external AI client access to your meetings. How to connect in five minutes, what leaves, what never leaves, and how the permissions are built.
- [Agent skills explained: what SKILL.md is and how to install one without a terminal](https://whisperer.one/en/blog/agent-skills-without-terminal/): SKILL.md is a plain-text instruction an AI assistant reads before a task. What is inside it, how it differs from MCP, how to install one without a terminal, and what to check first.
- [Meeting minutes: what they are, how to structure them, and how to take them](https://whisperer.one/en/blog/meeting-minutes/): Meeting minutes are a short record of what was decided, who owns it and by when. Seven sections, how much detail to keep, a template and a builder.
- [Meeting agenda: what belongs on it, how items get submitted, six formats](https://whisperer.one/en/blog/meeting-agenda/): A meeting agenda is a list of items, each with a verb, an expected outcome and a time box. Selection criteria, a skeleton agenda, six formats and a checklist.
- [Transcripts as a language-learning tool: reviewing your own calls](https://whisperer.one/en/blog/transcripts-language-learning/): How to use a transcript of your own speech to spot recurring mistakes, poor constructions and filler words.
- [Structured interviews: assessing candidates from the transcript, not from impressions](https://whisperer.one/en/blog/structured-interview/): Why memory fails you on the fourth interview in a row, and how to reduce assessment to comparable criteria instead of gut feel.
- [Customer discovery: pulling insights out of 20 interviews without drowning](https://whisperer.one/en/blog/customer-discovery/): A working scheme: from transcripts to coded quotes, from codes to patterns, from patterns to product decisions.

## Languages

Every documentation page exists in all 16 interface languages at `/docs/<lang>/`. The
machine-readable layer above is English only, by design: it is read by models, not by people.

- [English](https://whisperer.one/en/) · docs: https://whisperer.one/docs/en/
- [中文（繁體）](https://whisperer.one/zh/) · docs: https://whisperer.one/docs/zh/
- [Español](https://whisperer.one/es/) · docs: https://whisperer.one/docs/es/
- [Русский](https://whisperer.one/) · docs: https://whisperer.one/docs/ru/
- [हिन्दी](https://whisperer.one/hi/) · docs: https://whisperer.one/docs/hi/
- [العربية](https://whisperer.one/ar/) · docs: https://whisperer.one/docs/ar/
- [Português](https://whisperer.one/pt/) · docs: https://whisperer.one/docs/pt/
- [Français](https://whisperer.one/fr/) · docs: https://whisperer.one/docs/fr/
- [Italiano](https://whisperer.one/it/) · docs: https://whisperer.one/docs/it/
- [Deutsch](https://whisperer.one/de/) · docs: https://whisperer.one/docs/de/
- [日本語](https://whisperer.one/ja/) · docs: https://whisperer.one/docs/ja/
- [한국어](https://whisperer.one/ko/) · docs: https://whisperer.one/docs/ko/
- [Bahasa Indonesia](https://whisperer.one/id/) · docs: https://whisperer.one/docs/id/
- [Türkçe](https://whisperer.one/tr/) · docs: https://whisperer.one/docs/tr/
- [Tiếng Việt](https://whisperer.one/vi/) · docs: https://whisperer.one/docs/vi/
- [ไทย](https://whisperer.one/th/) · docs: https://whisperer.one/docs/th/

## Legal

- [Privacy Policy](https://whisperer.one/privacy/)
- [Terms of Use](https://whisperer.one/terms/)
- [Consent to Processing of Personal Data](https://whisperer.one/consent/)
- [Consent to Marketing Communications](https://whisperer.one/consent-marketing/)
- [Refund Policy](https://whisperer.one/refund/)
- [Cookie Policy](https://whisperer.one/cookies/)
- [Contacts](https://whisperer.one/contacts/)

## Optional

- [MCP server](https://whisperer.one/mcp): JSON-RPC 2.0 over POST for external AI clients; see /llms/mcp.md
- [Sitemap](https://whisperer.one/sitemap.xml): all public URLs across the 16 languages
- [robots.txt](https://whisperer.one/robots.txt): machine-readable crawl rules
- [Email](mailto:support@whisperer.one): contact the team