Docs · EchoDiar

Install

Download the signed and notarized DMG from Releases, drag EchoDiar to Applications.
Needs macOS 15+ on Apple Silicon. Apple Speech and Apple Foundation Models need macOS 26.
EchoDiar lives in the menu bar. Its Dock icon shows while one of its windows is open.
Updates itself: menu bar icon > Check for Updates…

Microphone: records your voice.
System Audio Recording: records the meeting's audio. The first-run onboarding tests it and opens the right Privacy & Security pane.
Accessibility (optional): only to keep the floating indicator on the meeting window.
Tell the people you record. Onboarding and Settings > General have a Copy consent message button.

Record one app's audio or all system audio, plus your mic. Mic and system audio go to separate channels of one file.
When an app's audio cannot be isolated, EchoDiar records all system audio and says so.
Start or stop with Cmd+R in the app, or Cmd+Option+R from any app. Pause with Cmd+Shift+P.
Live level meters while recording. The menu bar icon shows idle, recording, paused and processing.
Pick the microphone, and what happens when it disconnects, in Settings > Recording.
Each recording is compressed to AAC (64 kbps by default). A recording cut short by a crash is recovered.

Offers to record when a meeting app starts using the mic: Zoom, Teams, Slack, Webex, FaceTime, Discord, Skype, and browsers for web calls such as Meet.
Per app: Ask, Always record or Ignore (browsers: Ask or Ignore).
A floating indicator shows while recording. Drag it, hide it while EchoDiar is in front, or attach it to the meeting window.
Auto-stop: when the meeting app quits, the call goes quiet or the screen locks, the indicator asks before stopping, with a 15 s countdown.

Starts on its own after Stop. Turn it off in Settings > Recording.
Engines: WhisperKit, Parakeet, Qwen3-ASR, and Apple Speech on macOS 26. WhisperKit, Parakeet and Qwen3-ASR models are downloaded only when you click Download in Settings > Transcription; macOS installs Apple Speech language assets the first time you use a language.
Speakers: your mic is Me. FluidAudio splits the meeting audio into Speaker 1, Speaker 2… Set the number of other speakers as a hint in Settings > Recording.
Live captions (optional): WhisperKit or Nemotron streaming while you record. The transcript made after Stop is the one saved.
Re-transcribe a conversation with another engine or language.
Can wait while the Mac is hot or in Low Power Mode.

Optional: OpenAI, Groq, Mistral, Gemini, ElevenLabs, Deepgram, AssemblyAI or a custom OpenAI-compatible endpoint. Set up ElevenLabs, Deepgram and AssemblyAI in Settings > Transcription > Transcription model, the others in Settings > AI.
The first run for each provider and address asks before any audio leaves your Mac. A changed URL asks again.
The mic and system channels are uploaded, and billed, separately.
API keys are stored in the Keychain.

Click a line to hear it. Space plays or pauses, Esc goes back.
Edit the title, rename speakers, copy the transcript or reveal the folder in Finder.

Open the AI panel with Cmd+I. Generate a summary or ask questions about a conversation.
Answers cite [mm:ss] timestamps. Click one to jump to that moment in the transcript and recording.
Response language, for summaries and answers: automatic (the transcript's language for summaries, the question's for answers), English, French or Vietnamese.
On-device: MLX models, and Apple Foundation Models on macOS 26.
Local servers: LM Studio, Ollama, Jan, llama.cpp, vLLM. Scan finds the ones running on this Mac.
Cloud APIs: OpenAI, Anthropic, xAI, Gemini, Mistral, Azure OpenAI, OpenRouter, Groq, DeepSeek or a custom endpoint. Keys go in the Keychain.
Subscription CLIs: Claude Code, Codex, OpenCode or Gemini CLI, with your own login.
Copy as prompt copies the transcript and your question, ready to paste into any chat app.

Data lives in ~/Library/Application Support/EchoDiar. Settings > Storage shows the space used.
Auto-delete: once a day, moves transcribed conversations older than an age you set to the Trash, whole or audio only.
Optionally delete the audio once a transcription succeeds. The transcript, summary and chat stay.
Choose the compression bitrate, or keep the uncompressed audio too.

Open with Cmd+,. Sections: General, Recording, Transcription, AI, Storage, Shortcuts, About.
Change the global record shortcut, and view the app's shortcuts, in Settings > Shortcuts.
Launch at login and the floating indicator are in Settings > General.