# HyperWhisper

> AI-powered speech-to-text transcription for macOS

## Docs

- [Advanced Settings](https://hyperwhisper.com/docs/advanced-settings.md): Reference for HyperWhisper's advanced recording and storage settings — max duration, audio sample rate, audio file retention, and history limits.
- [API Keys](https://hyperwhisper.com/docs/api-keys.md): Set up API keys for cloud transcription and post-processing providers.
- [Create a new Mode](https://hyperwhisper.com/docs/api-reference/create-a-new-mode.md)
- [Delete a Mode](https://hyperwhisper.com/docs/api-reference/delete-a-mode.md): Refuses to delete the last remaining Mode (returns ok=false / INVALID_REQUEST).
- [Fetch one Mode](https://hyperwhisper.com/docs/api-reference/fetch-one-mode.md)
- [Fetch one recording](https://hyperwhisper.com/docs/api-reference/fetch-one-recording.md)
- [List models](https://hyperwhisper.com/docs/api-reference/list-models.md)
- [List saved Modes](https://hyperwhisper.com/docs/api-reference/list-saved-modes.md)
- [MCP Setup](https://hyperwhisper.com/docs/api-reference/local-api/mcp-setup.md): Wire HyperWhisper's local API into Cursor, Claude Desktop, or Claude Code as an MCP server so any agent can transcribe and post-process through the running app.
- [Local API Overview](https://hyperwhisper.com/docs/api-reference/local-api/overview.md): HTTP API exposed by HyperWhisper.app on 127.0.0.1 when the user enables it. Off by default.
- [Partial-field update](https://hyperwhisper.com/docs/api-reference/partial-field-update.md)
- [Rewrite text with AI post-processing](https://hyperwhisper.com/docs/api-reference/rewrite-text-with-ai-post-processing.md)
- [Search past transcripts](https://hyperwhisper.com/docs/api-reference/search-past-transcripts.md)
- [Server + provider snapshot](https://hyperwhisper.com/docs/api-reference/server-+-provider-snapshot.md): Unauthenticated. Returns server identity, the cached cloud-provider health snapshot, and the installed local-model inventory.
- [Transcribe audio](https://hyperwhisper.com/docs/api-reference/transcribe-audio.md): Accepts either an absolute `file` path OR an `audio_base64` + `mime_type` pair. The engine + model can come from a saved `mode_id`, from explicit `engine`/`model`/`language` fields, or a mix (mode supplies defaults and per-call fields override).
- [Appearance Settings](https://hyperwhisper.com/docs/appearance-settings.md): How to change HyperWhisper's color theme between light, dark, and system default on Windows and iOS.
- [Audio Input Volume](https://hyperwhisper.com/docs/audio-input.md): Check and adjust your microphone volume, and configure HyperWhisper's Sound settings for the best transcription quality.
- [Auto Paste & Clipboard Behavior](https://hyperwhisper.com/docs/auto-paste.md): How HyperWhisper copies, restores, and optionally pastes your transcript automatically.
- [Backup & Export Settings](https://hyperwhisper.com/docs/backup-export-settings.md): Export your settings, modes, vocabulary, and API keys to a file and restore them on another device or after a reinstall.
- [Best Practices](https://hyperwhisper.com/docs/best-practices.md): Tips for getting the most accurate transcriptions with HyperWhisper.
- [Providers](https://hyperwhisper.com/docs/choosing-a-provider.md): Pick a transcription model by language accuracy and cost. Covers HyperWhisper Cloud tiers, silence-free billing, and BYOK alternatives.
- [HyperWhisper Cloud Credits](https://hyperwhisper.com/docs/cloud-credits.md): How credits work, how to check your balance, and how to purchase more.
- [Custom OpenAI-Compatible Endpoints](https://hyperwhisper.com/docs/custom-endpoints.md): Add any OpenAI-compatible server — Ollama, LM Studio, OpenRouter, or your own — as a post-processing provider in HyperWhisper.
- [Data Privacy](https://hyperwhisper.com/docs/data-privacy.md): How HyperWhisper handles your audio data, and how to opt out of model training when you bring your own API keys.
- [Developer Mode](https://hyperwhisper.com/docs/developer-mode.md): Smart file tagging with @ mentions for coding with AI post-processing.
- [Transcribe a File](https://hyperwhisper.com/docs/file-transcription.md): Import an existing audio or video file and transcribe it with any HyperWhisper mode.
- [General Settings](https://hyperwhisper.com/docs/general-settings.md): Configure how HyperWhisper launches, behaves in the background, handles updates, and reports errors.
- [Fixing Transcription Hallucinations](https://hyperwhisper.com/docs/hallucinations.md): Why speech-to-text models sometimes invent words, and what you can do about it.
- [Viewing Transcription History](https://hyperwhisper.com/docs/history.md): Browse, search, filter, and manage every transcription you've made — including playback, editing, and retrying failed jobs.
- [Introduction](https://hyperwhisper.com/docs/index.md): Welcome to the HyperWhisper help center. Learn how to use HyperWhisper for AI-powered speech-to-text transcription on macOS.
- [Keep Microphone Warm](https://hyperwhisper.com/docs/keep-microphone-warm.md): Reduce push-to-talk startup delay by keeping your microphone session open between recordings.
- [Keyboard Shortcuts & Accessibility](https://hyperwhisper.com/docs/keyboard-shortcuts.md): Customize global hotkeys, configure push-to-talk, set up Quick Capture, and understand what the menu bar icon shows.
- [Language & Detection](https://hyperwhisper.com/docs/language-detection.md): Configure the transcription language per mode, understand automatic language detection, and learn how language choice affects engine availability, vocabulary boosting, and AI post-processing.
- [Pricing & Trial Limits](https://hyperwhisper.com/docs/licensing.md): Trial vs Pro tiers, what cloud credits are, how to purchase, and how to manage your billing.
- [Local API Server](https://hyperwhisper.com/docs/local-api.md): Enable HyperWhisper's built-in HTTP server to drive transcription from MCP clients, Shortcuts, Raycast, or any shell script.
- [Mute Audio While Recording](https://hyperwhisper.com/docs/media-control.md): Automatically silence other audio playing on your computer while you dictate, then restore it when you're done.
- [Menu Bar & Tray Controls](https://hyperwhisper.com/docs/menu-bar.md): Quick access to recording, microphone switching, mode switching, and settings without opening the main window.
- [Select a Microphone or Audio Input Device](https://hyperwhisper.com/docs/microphone-selection.md): Choose which microphone or audio input device HyperWhisper records from, and how it handles device changes at runtime.
- [Models](https://hyperwhisper.com/docs/models.md): Every model HyperWhisper offers — speech-to-text and post-processing, on-device and cloud — and why each one exists. Pick by privacy, language coverage, speed, accuracy, and cost.
- [Network Filtering](https://hyperwhisper.com/docs/network-filtering.md): Whitelist domains and configure network access for HyperWhisper's transcription and AI features
- [Text Output & Formatting](https://hyperwhisper.com/docs/output-settings.md): Control how HyperWhisper delivers transcribed text — auto-paste, filler-word removal, smart capitalization, and clipboard behavior.
- [Performance Tips](https://hyperwhisper.com/docs/performance-tips.md): How to get the fastest transcriptions, lowest latency, and best resource use out of HyperWhisper — whether you're on cloud or local models.
- [macOS Permissions](https://hyperwhisper.com/docs/permissions.md): What permissions HyperWhisper needs on macOS, when each is prompted, what breaks without it, and how to grant them in System Settings.
- [Provider Health & Automatic Failover](https://hyperwhisper.com/docs/provider-health.md): How HyperWhisper monitors cloud provider status, validates API keys, and automatically retries a backup provider when one fails.
- [The Recording Window](https://hyperwhisper.com/docs/recording-window.md): What the recording window shows during a recording and how to interact with it on macOS, Windows, and iOS.
- [Sound Effects](https://hyperwhisper.com/docs/sound-effects.md): Audio feedback that confirms when HyperWhisper starts and stops recording.
- [Streaming Transcription](https://hyperwhisper.com/docs/streaming-settings.md): Configure HyperWhisper's real-time streaming mode — provider, language, keyboard shortcut, and Deepgram-specific options.
- [Support & Refunds](https://hyperwhisper.com/docs/support.md): How to contact support, report bugs, and request a refund.
- [Transcribing System Audio](https://hyperwhisper.com/docs/system-audio.md): How to transcribe meetings, videos, or anything else playing on your computer.
- [System Requirements](https://hyperwhisper.com/docs/system-requirements.md): Supported operating systems, processor architectures, and hardware notes for HyperWhisper on macOS and Windows.
- [Transcription Modes](https://hyperwhisper.com/docs/transcription-modes.md): Configure how HyperWhisper transcribes and formats your speech. Modes bundle your transcription engine, language, AI post-processing, and formatting options into reusable profiles.
- [Troubleshooting](https://hyperwhisper.com/docs/troubleshooting.md): Fixes for common HyperWhisper problems — recording failures, blank transcripts, permission errors, cloud provider issues, and model downloads.
- [App Updates](https://hyperwhisper.com/docs/updates.md): How HyperWhisper updates itself on macOS and Windows, and how to check for updates manually.
- [Custom Vocabulary](https://hyperwhisper.com/docs/vocabulary.md): Teach HyperWhisper the names, acronyms, and phrases it should never miss — and share your list across devices.
- [Cloud Sync Vocabulary Across Devices](https://hyperwhisper.com/docs/vocabulary-cloud-sync.md): Keep your custom vocabulary in sync across all your Apple devices using iCloud.
- [Import & Export Vocabulary](https://hyperwhisper.com/docs/vocabulary-import-export.md): Move your custom vocabulary between devices and platforms using CSV files and universal .hwbackup.json backups.
- [Voice Activity Detection & Silence Trimming](https://hyperwhisper.com/docs/voice-activity-detection.md): Automatically remove silence from your recordings before transcription to reduce costs and improve speed.
- [Voice Coding in AI IDEs](https://hyperwhisper.com/docs/voice-coding.md): Use HyperWhisper with Cursor, Claude Code, and other AI-powered editors to dictate prompts, tag files by voice, and let agents respond to your spoken questions.
- [Voice Commands](https://hyperwhisper.com/docs/voice-commands.md): Examples of phrasing that HyperWhisper's prompt builder understands while it cleans up your dictation.
- [Windows Getting Started](https://hyperwhisper.com/docs/windows-getting-started.md): Install HyperWhisper on Windows and make your first recording.
- [Windows Permissions](https://hyperwhisper.com/docs/windows-permissions.md): What access HyperWhisper requests on Windows, when each is needed, what breaks without it, and how to fix common problems.
- [Windows FAQ](https://hyperwhisper.com/docs/windows/faq.md): Troubleshooting and answers for HyperWhisper on Windows.

## OpenAPI Specs

- [openapi](https://hyperwhisper.com/docs/api-reference/openapi.json)