omniscribe
Streams captured meeting and microphone audio to Deepgram for live transcription using a user-provided API key, producing labelled channel-tagged transcript files and status/cost metadata.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Omniscribe
BETA (v1.0.0rc1). Experimental. Review the transcript and verify your audio routing before relying on it.
Status: release candidate v1.0.0rc2. Offline tests pass (67). Live capture on real hardware and with Deepgram has not been verified. Not published.
Omniscribe is a macOS command-line tool and local MCP server for live meeting transcription. It captures the remote side of an online meeting (through BlackHole) and your microphone, streams them to Deepgram with your own API key, and writes labelled, channel-tagged transcript files to a folder you choose. It can also help an assistant write a summary, one incremental step at a time.
Language: required, with no default. Set
language = "id"for Indonesian inconfig.toml, or pass--language(CLI) /language(MCP) per session. Missing language is refused before consent, capture or upload.Channels:
REMOTE(meeting audio) andCAPTAIN(your microphone). Labels identify the channel, not individual speakers.Modes:
online(remote + microphone) andin-person(microphone only).Recording: no raw audio is kept by default. Optional local WAV recording (
record_wav) is off unless you turn it on.Consent: every
startandapproveasks for a local, humanyeson your Mac, whatever theconsentsetting says. A legacyconsent = "all-meetings"does not skip the prompt. An MCP client cannot give consent.
Requirements
macOS, Python 3.11 or newer.
SoX with CoreAudio support (
brew install sox).BlackHole 16ch, for
onlinemode only.A Deepgram API key, for real transcription.
Related MCP server: openwhispr-transcribe
Install
python3 -m venv .venv
source .venv/bin/activate
python3 -m pip install -e .This installs three commands: omniscribe, omniscribe-summary and omniscribe-mcp. Full audio setup is in the macOS setup guide.
Put your key in the environment, never in a file, flag or config:
export DEEPGRAM_API_KEY="YOUR_DEEPGRAM_API_KEY"Create the private config in the output folder (default ~/.live-meeting-transcribe/):
mkdir -p "$HOME/.live-meeting-transcribe"
cp config.example.toml "$HOME/.live-meeting-transcribe/config.toml"Quick start
Start a meeting. Omniscribe asks for consent before it connects or captures anything:
omniscribe start --name team-syncFor an in-person meeting, use the microphone only:
omniscribe start --name team-sync --mode in-personMeeting names may contain letters, digits, _ and - (1 to 80 characters). A dated folder <YYYY-MM-DD>-<name>/ is created. Existing folders are never overwritten, so choose a new name for each meeting.
Prepare, then approve
prepare stages a session without capturing anything. approve then asks for the local yes:
omniscribe prepare --name team-sync --mode online
omniscribe approveTyping no exits with code 2, removes the staged session, and creates no meeting folder. Closing the input without a yes (for example Ctrl-D) has the same result: exit code 2, the staged session removed, and no meeting folder. A missing or invalid language is also refused with exit code 2, before consent, before capture and before any upload, with a short message that names the setting to change. approve requires the key unless the session was prepared with --mock.
Stop
Press Ctrl-C in the capture terminal, or
from another terminal, with the same output root:
omniscribe stop(add--waitto wait up to 2 seconds for the lock to clear).
Do not force-kill the process. Orderly shutdown finalises the transcript and removes the ACTIVE lock. After a crash, check that the process is gone before removing a stale ACTIVE file by hand.
Status
omniscribe status
omniscribe status --meeting-dir <folder>This prints JSON: the lifecycle state (ACTIVE, PREPARED, STOPPED or IDLE), the session status and the summary coverage.
What it writes
Output root precedence: --out → OMNISCRIBE_HOME → LMT_HOME → ~/.live-meeting-transcribe. The config is <output_root>/config.toml unless --config is given.
Each meeting folder contains:
File | Contents |
| Labelled final lines ( |
| Raw final recognition events with meeting offsets. |
| Captain lines removed by the echo filter, kept for audit. |
| Status snapshot: mode, language, streams, elapsed time, estimated cost. |
| Session log written at shutdown. |
| Final lines merged by start time. |
| Per-meeting caveats. |
| Only when |
| Summary files, written only by the summary helper. |
Summaries
Summary text is written by a person or an assistant, not by the capture tool. The helper omniscribe-summary only tracks which lines are covered:
omniscribe-summary delta <meeting-dir> # stage the new lines
omniscribe-summary check <meeting-dir> # validate the draft summary
omniscribe-summary commit <meeting-dir> # advance the cursor if valid
omniscribe-summary status <meeting-dir>A summary must start with Updated: HH:MM:SS | lines covered: N and contain the sections ## Summary, ## Actions, ## Decisions and ## Open questions. A failed check leaves the cursor where it was.
MCP server
omniscribe-mcp is a local stdio MCP server (server name omniscribe). It exposes five tools: omniscribe_prepare_session, omniscribe_get_status, omniscribe_stop_session, omniscribe_get_transcript_delta and omniscribe_save_summary. Setup examples are in examples/mcp/ for Claude, Codex and Pi.
The MCP server cannot start capture, cannot give consent, and rejects arguments named consent, approve, auto_approve, yes, api_key or deepgram_api_key. A prepared session still needs omniscribe approve in your terminal. The output root must contain config.toml, with language set there or passed in the tool call, before omniscribe_prepare_session works.
Configuration
Start from config.example.toml. Keys: consent, mode, language, mic, remote, echo, record_wav, exclude_titles, captain_highpass_hz, echo_text_threshold, echo_correlation_threshold. The full table is in the setup guide. Meetings whose exact name is listed in exclude_titles are refused.
Exit codes
Code | Meaning |
| Success. |
| Runtime or argument error, or a stream was |
| Refused before capture: key missing, excluded title, missing or invalid language, |
Privacy
Live sessions send both audio channels to Deepgram. Transcript text and service metadata are written under the output root. Keep that folder private, and get consent from the participants as your policy and local law require. Transcripts are not verbatim or legally verified records.
Limitations
Offline tests use local mocks and recorded WAV files. They do not test Deepgram, your devices or Zoom routing.
Recognition quality varies with the microphone, accent and room noise. Labels do not identify speakers.
The echo filter is heuristic, with provisional thresholds. It may miss speech or remove valid speech.
Audio can be lost during a reconnect. The client retries at most three times.
Estimated cost is a list-rate calculation, not a bill.
Development
python3 -m unittest discover -s tests -vThe offline suite needs no key and no devices. Run it with DEEPGRAM_API_KEY unset.
License
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Start meetings and work with meeting transcripts, notes, recordings and follow-up tasks.
Transcripts, recaps, and action items. Authenticated; OAuth 2.1 via Keycloak.
Send a bot to your Google Meet, Zoom or Teams call for notes or your update; get the transcript.
Transcribe recordings into a speaker-labelled transcript with timestamps and a summary.
Related MCP Servers
- AlicenseAqualityDmaintenanceRead-only access to your Gilbert meetings, transcripts and summaries over MCP — list, search, and fetch transcripts and summaries.535 npm1MIT
- AlicenseNot gradedqualityDmaintenanceProvides tools for local meeting speaker analysis and hybrid cloud transcription, supporting resumable transcription and alignment.MIT
- AlicenseAqualityCmaintenanceEnables listing a signed-in user's recent meetings and retrieving speaker-attributed transcripts or raw WebVTT through Microsoft Graph with secure delegated authentication.5MIT
- AlicenseNot gradedqualityBmaintenanceLets assistants manage private, locally transcribed meeting and interview recordings: start/stop sessions, list and search transcripts, retrieve paginated transcript text, add notes/tags, and export recordings.MIT