Call Recorder MCP
This server records macOS call and meeting audio locally, transcribes it with Whisper, and gives Claude tools for live call assistance and transcript management.
Start recording from system audio, WhatsApp, Teams, Zoom, Slack, FaceTime, browsers, specific apps, or a bundle ID prefix, with options for title, mic, language, speaker count, and live transcription.
Check whether recording is active, elapsed time, captured apps, and live audio levels.
Follow a live call via
get_live_transcriptto see speech about a second after each sentence and get real-time help on questions and follow-ups.Stop recording, transcribe the call, and retrieve the transcript when ready.
Access or re-transcribe existing recordings, including choosing another language or separating multiple speakers.
Transcribe existing audio/video files such as voice notes or meeting recordings.
Rename speaker labels to real names, list recent recordings and transcription states, and list available audio sources and default microphone/output.
Captures audio from Arc so browser-based calls and meetings can be recorded and transcribed locally.
Captures audio from Firefox so browser-based calls and meetings can be recorded and transcribed locally.
Captures and transcribes Google Meet meetings held in a browser on macOS, using browser/app audio capture and local Whisper transcription.
Captures audio from Safari so browser-based calls and meetings can be recorded and transcribed locally with speaker separation.
Records and transcribes Slack calls on macOS via per-app audio capture, returning local transcripts with speaker labels.
Records and transcribes WhatsApp calls on macOS, including CallKit audio routed through Apple's avconferenced service, with local transcription and speaker separation.
Records and transcribes Zoom meetings on macOS via per-app audio capture, including separate microphone and remote tracks with optional speaker separation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Call Recorder MCP Record my WhatsApp call and transcribe it when the call ends"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Call Recorder MCP
Model Context Protocol server that records calls on macOS (WhatsApp, Teams, Zoom, Slack, FaceTime, Google Meet or any meeting in the browser) and transcribes them locally with Whisper. Ask Claude to record, say when the call is over, and get the transcript back in the conversation, with who said what.
Audio never leaves your Mac: capture, transcription and speaker separation all run locally. Only the transcript text goes to Claude, when Claude reads it.
Features
Records both sides of a call as two aligned tracks: your microphone and what the apps play. Uses Core Audio process taps (macOS 14.4+), so no virtual audio driver such as BlackHole is needed.
Per-app capture: record only WhatsApp, Teams or the browser, or the whole system output. The capture follows the app if it starts playing late, and survives switching to AirPods mid-call.
Local transcription with whisper.cpp (
large-v3-turbo, Metal accelerated) and Silero voice activity detection, which keeps Whisper from inventing text during silences. About 75 s for 18 minutes of call on an M-series Mac.Live help during a call: Claude follows the conversation about a second behind and, as it goes, tells you which of your questions got answered, where the other side stayed vague, and what to ask next.
Who said what: "Me" (your mic) and "Other side" (what the apps play). Without headphones your mic also hears the other side; those echoes are removed.
Several people on the other side: give their number and their voices are separated (Speaker 1, 2...), then renamed to real names in one call.
Custom vocabulary so product, company and people names are spelled right.
Works with existing files too: WhatsApp voice notes, meeting recordings, any audio or video format ffmpeg reads.
A mixed
conversation.wavof each call, to listen to.20 languages: tool replies, transcript labels ("Me", "Speaker 1"...) and the macOS permission prompts follow your Mac's language, and transcription defaults to it: Arabic, Chinese (Simplified and Traditional), Dutch, English, French, German, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese (Brazil and Portugal), Russian, Spanish, Swahili, Thai, Turkish and Vietnamese. Set
CALL_RECORDER_LOCALEto choose. Transcription itself works in any language Whisper supports.
Related MCP server: macwhisper-mcp-server
Requirements
macOS 14.4 or later. Apple Silicon recommended.
Homebrew packages:
brew install whisper-cpp ffmpeg uvXcode Command Line Tools (to compile the capture helper):
xcode-select --installAbout 650 MB of disk space for the models.
Quick install
Build the capture helper and download the models (run it again after each upgrade):
uvx --from git+https://github.com/morganseznec/call-recorder-mcp call-recorder-setupRegister the server in Claude Code:
claude mcp add call-recorder -s user -- uvx --from git+https://github.com/morganseznec/call-recorder-mcp call-recorder-mcpFor Claude Desktop, add the same command to
~/Library/Application Support/Claude/claude_desktop_config.jsonand restart it:{ "mcpServers": { "call-recorder": { "command": "/opt/homebrew/bin/uvx", "args": ["--from", "git+https://github.com/morganseznec/call-recorder-mcp", "call-recorder-mcp"] } } }On the first recording, macOS asks whether CallRecorder may use the microphone and record audio from other apps. Accept both. If you missed the prompt: System Settings > Privacy & Security > Microphone (and Screen & System Audio Recording).
call-recorder-setup signs the helper with your first "Apple Development" certificate if you have one, so macOS keeps the permissions across upgrades. Without one it uses an ad-hoc signature, and macOS asks again after each rebuild.
Using it from Claude
You never call the tools yourself: talk to Claude and it picks them.
What you say | What happens |
"Record my WhatsApp call" |
|
"The call is over, transcribe it" |
|
"Record the Teams meeting, there are 4 people on the other side" |
|
"Speaker 1 is Alice, speaker 2 is Bob" |
|
"Transcribe this voice note ~/Downloads/note.opus" |
|
"Transcribe the last call again, in Spanish" |
|
"Is it recording properly?" |
|
It works the same in any language: "Enregistre mon appel WhatsApp", "Graba mi llamada de WhatsApp"...
A transcript looks like this:
# Product sync
- Date: 2026-10-27 12:10:37
- Source: teams
- Duration: 00:18:44
- Participants: Alice, Me, Speaker 2
- Language: en
## Transcript
**[00:00:02] Alice**: Hi everyone, let's go over version 2.
**[00:00:06] Me**: On my side the iOS build is ready, it's in TestFlight.Live help during a call
Give Claude the context of the call and the questions you want to ask, then start a live recording:
I'm calling a supplier about the v2 delivery. I want to know the delivery date, the budget and who validates the release. Record the WhatsApp call live and help me dig in when the answers are vague.
Claude starts the recording with live=true, then follows the call with get_live_transcript in a loop, in the same reply. After each exchange it tells you, in a few lines, which questions are covered, which answers stayed vague or evasive, and one or two follow-up questions to ask now. It stops when you stop the recording.
Each sentence reaches Claude about 1 second after it ends: a
whisper-serverkeeps the model in memory and a streaming voice detector (Silero, through sherpa-onnx) cuts each side into sentences as they come.The live text is a draft: no speaker separation, less context per sentence. The final transcript, made when the call ends, is unchanged.
In live mode the transcript goes to Claude continuously during the call.
How it works
Claude ──MCP──> call-recorder-mcp ──open──> CallRecorder.app ──> mic.wav + remote.wav
│
├──> live job (optional): streaming VAD ──> whisper-server ──> live.jsonl
└──> background job: VAD or diarization ──> whisper.cpp ──> transcript.mdCapture.
CallRecorder.appis a small Swift helper (macos/main.swift). It taps the audio of the chosen processes (Core Audio process tap + private aggregate device) and records the microphone (AVAudioEngine), writing two mono 48 kHz tracks kept aligned on the host clock. It is launched throughopenso that macOS asks for the permissions under its own name, whichever MCP client started the server.WhatsApp calls go through CallKit: their audio is played by Apple's
avconferencedservice, not by WhatsApp itself. Thewhatsappsource includes it.Transcription runs in a detached process, so a long call never times out a tool call:
stop_recordingwaits up to 30 s, then Claude pollsget_transcript. Each track is cut into utterances and every utterance is transcribed as its own short file, in a single whisper.cpp run. This keeps timestamps exact and lets the vocabulary apply everywhere.Speaker separation uses sherpa-onnx: pyannote segmentation 3.0 and CAM++ voice embeddings.
Speaker separation: why you give the number of people
Measured on a real 18-minute WhatsApp call between two people, both sides mixed into one file:
Setup | Result |
CAM++ embeddings, number of speakers given | 99.7 % of speaking time attributed to the right person |
WeSpeaker ResNet34 embeddings, number given | about 70 % |
Automatic speaker count, any threshold tried | one person split into 2 to 12 "voices", or distinct voices merged |
Short replies ("ok", "uh-huh") are too brief for a reliable voice signature, so automatic counting over-splits on real calls. With the number of people given, the clustering is reliable. Claude asks you for it on a group call.
Limits: very short interjections and overlapping speech can be misattributed, and two very similar voices can be merged.
Vocabulary
Whisper misspells names it does not know. List them in ~/Library/Application Support/call-recorder-mcp/vocabulary.txt, one per line (# for comments). call-recorder-setup creates it from an example.
Only list words people actually say: Whisper tends to insert listed names where it hears something close.
Configuration
All optional, set with -e NAME=value in claude mcp add:
Variable | Default | Purpose |
|
| Where recordings and transcripts go |
| your Mac's language | Language of replies and transcript labels: |
| same as the locale | Default transcription language, as a Whisper code ( |
|
| Vocabulary file |
|
| Helper app, models, vocabulary |
|
| Any whisper.cpp model |
| first Apple Development identity | Code signing identity used by |
Each recording gets its own folder, <CALL_RECORDER_DIR>/<date>_<time>_<title>/:
File | Content |
| The transcript, for people and for programs |
| Both sides mixed |
| Your microphone, the other side (or |
| Title, settings and state |
Recordings stop automatically after 4 hours.
Tool reference
Tool | Purpose |
| Start recording. |
| What was said since the cursor |
| Elapsed time, captured apps, live levels (-120 dB on a side means nothing is captured) |
| Stop, mix |
| Transcript of a recording ( |
| Transcribe again, e.g. in another language or to separate voices |
| Transcribe an existing audio or video file |
| Replace "Speaker 1"... with real names |
| Latest recordings and their transcription state |
| Apps currently using audio, default microphone and output |
Privacy and consent
Recording a conversation without the other people's consent is illegal in many countries (in France, article 226-1 of the Code pénal). Tell the people you are recording. Audio and transcripts are stored on your Mac, in the folder above; the transcript text is sent to Claude when it reads it, continuously in live mode.
Development
git clone https://github.com/morganseznec/call-recorder-mcp
cd call-recorder-mcp
uv run --extra dev pytest
uv run --extra dev ruff check . && uv run --extra dev ruff format --check .
uv run call-recorder-setup --skip-models # rebuild the helper after editing main.swiftTo run your checkout in Claude Code instead of the published version:
claude mcp add call-recorder -s user -- uv run --directory "$PWD" call-recorder-mcpVersioning and changelog
Semantic Versioning. See CHANGELOG.md.
License
Available Tools
10 toolsget_live_transcriptARead-onlyIdempotent
Live transcript of the recording in progress (started with live=true): what was said since
the cursor since, about a second after each sentence ends. Waits up to wait_seconds for new
speech. Rough text: the final transcript after the call is more accurate.
To follow a call and help the user in real time, call it in a loop within the same turn,
passing the returned cursor as since. After each batch, tell the user in a few lines (they
are on the call, keep it short): which of their planned questions got answered, where the
other side stayed vague, evasive or unconvincing, and one or two precise follow-up questions
to ask now. Say nothing when a batch brings nothing useful. Stop when the recording is over.
Inputs: since, wait_seconds. Returns: result
get_transcriptARead-onlyIdempotent
Transcript of a recording ("latest" or the folder name), waiting up to wait_seconds if it is still running.
Inputs: recording, wait_seconds. Returns: result
list_audio_sourcesBRead-onlyIdempotent
Apps currently using audio (to choose the source), and the default microphone and output.
Inputs: no named parameters. Returns: result
list_recordingsCRead-onlyIdempotent
Latest recordings and their transcription state.
Inputs: limit. Returns: result
recording_statusARead-onlyIdempotent
Whether a recording is in progress, for how long, and the recent sound levels of each side (-120 dB on the other side means no sound is being captured).
Inputs: no named parameters. Returns: result
rename_speakersADestructiveIdempotent
Replace speaker labels in a transcript with real names, e.g. {"Speaker 1": "Alice"} (labels are in the user's language, as shown in the transcript). Returns the updated transcript.
Inputs: names (required), recording. Returns: result
start_recordingA
Start recording a call or a conversation.
source: "system" (all the Mac's audio, the safest), "whatsapp", "teams", "zoom", "slack", "facetime", "browser" (all browsers), "chrome", "safari", "firefox", "arc", "edge", or a bundle ID prefix (e.g. "com.microsoft.teams2"). title: name of the conversation (used for the folder name). include_mic: also record the microphone (the user's voice). language: transcription language ("en", "fr", "auto"...). Defaults to the user's language. speakers: number of people on the other side (default 1). Above 1, their voices are separated in the transcript (Speaker 1, Speaker 2...). live: also transcribe as the call goes, to follow it with get_live_transcript. Use it when the user wants help during the call (questions to ask, answers to dig into).
Inputs: live, title, source, language, +2 more. Returns: result
stop_recordingAIdempotent
Stop the recording in progress and start its transcription.
speakers: number of people on the other side, if different from the one given at start (0 = unchanged). For a group call, ask the user. language: overrides the language chosen at start. Returns the transcript if it is ready within wait_seconds, otherwise says to call get_transcript later.
Inputs: language, speakers, transcribe, wait_seconds. Returns: result
transcribe_fileB
Transcribe an existing audio or video file (WhatsApp voice note .opus, .m4a, .mp3, .mp4, meeting recording...), copied into a new recording folder.
speakers: total number of people speaking in the file (above 1, their voices are separated into Speaker 1, Speaker 2...).
Inputs: path (required), title, language, speakers, +1 more. Returns: result
transcribe_recordingBDestructiveIdempotent
Transcribe an existing recording again, e.g. in another language, or to separate voices: speakers = number of people on the other side (0 = unchanged).
Inputs: language, speakers, recording, wait_seconds. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool has a distinct role across source discovery, recording control, monitoring, transcription, and transcript cleanup. Live versus final transcripts and retranscribing recordings versus importing files are clearly differentiated.
All tools use readable snake_case, and nearly all follow a consistent verb_noun pattern. The noun-first recording_status is a minor deviation from names such as get_transcript and list_recordings.
Ten tools are well scoped to call recording and transcription without obvious redundancy. Each supports a meaningful part of the workflow, including optional live assistance and external-file transcription.
The surface covers the core lifecycle from choosing an audio source through recording, status checks, transcription, retrieval, and speaker renaming. Recording management is somewhat thin because there is no apparent way to delete recordings or inspect detailed metadata beyond the latest-recordings list.
Maintenance
Related MCP Connectors
Ask Claude about your meetings: summaries, action items and transcripts from Roomtone
Turn calls and notes into process flow diagrams in Claude, ChatGPT, VS Code, Cursor, and Teams.
Transcribe audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A.
Transcribe audio and video and work with your transcript library from any AI app. 119 languages.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables bidirectional voice interaction for Claude Code using local speech-to-text and text-to-speech models optimized for Apple Silicon. It provides tools to listen to user speech via microphone and speak responses aloud through system speakers.16Apache 2.0
- AlicenseAqualityBmaintenanceEnables transcription, summarization, and action item extraction from audio files on your Mac using MacWhisper and Claude Desktop, all locally without any cloud APIs.73MIT
- AlicenseAqualityDmaintenanceCaptures and transcribes system audio in real-time using OpenAI Whisper, enabling meeting transcription, content creation, and accessibility through natural language.8268 npm3MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first meeting capture and transcription for Claude Code. Records audio from meeting apps, transcribes locally with whisper.cpp, and produces structured notes via Claude.1Apache 2.0