Local-first meeting transcription and summarization CLI. Record, transcribe, and summarize meetings and system audio entirely on your machine – no cloud, no bots, no data leaving your device.
System audio capture requires macOS 14.2 or later. Other platforms can use the sounddevice backend with an external audio source.
ownscribe does not:
- send audio to external servers
- upload transcripts
- require cloud APIs
- store data outside your machine
All audio, transcripts, and summaries remain local.
- System audio capture — records all system audio natively via Core Audio Taps (macOS 14.2+), no virtual audio drivers needed
- Microphone capture — optionally record system + mic audio simultaneously with
--mic - WhisperX transcription — fast, accurate speech-to-text with word-level timestamps
- Speaker diarization — optional speaker identification via pyannote (requires HuggingFace token)
- Pipeline progress — live checklist showing transcription, diarization sub-steps, and summarization progress
- Local LLM summarization — structured meeting notes via Ollama, LM Studio, or any OpenAI-compatible server
- Summarization templates — built-in presets for meetings, lectures, and quick briefs; define your own in config
- Ask your meetings — ask natural-language questions across all your meeting notes; uses a two-stage LLM pipeline with keyword fallback
- One command — just run
ownscribe, press Ctrl+C when done, get transcript + summary
- macOS 14.2+ (for system audio capture)
- Python 3.12+
- uv
- ffmpeg —
brew install ffmpeg - Xcode Command Line Tools (
xcode-select --install) - One of:
Works with any app that outputs audio through Core Audio (Zoom, Teams, Meet, etc.).
Tip: Your terminal app (Terminal, iTerm2, VS Code, etc.) needs Screen Recording permission to capture system audio. Open the settings panel directly with:
open "x-apple.systempreferences:com.apple.preference.security?Privacy_ScreenCapture"Enable your terminal app, then restart it.
uvx ownscribeOn macOS, the Swift audio capture helper is downloaded automatically on first run.
# Clone the repo
git clone https://github.com/paberr/ownscribe.git
cd ownscribe
# Build the Swift audio capture helper (optional — auto-downloads if skipped)
bash swift/build.sh
# Install with transcription support
uv sync --extra transcription
# Pull a model for summarization (if using Ollama)
ollama pull mistralownscribe # records system audio, Ctrl+C to stopThis will:
- Capture system audio until you press Ctrl+C
- Transcribe with WhisperX
- Summarize with your local LLM
- Save everything to
~/ownscribe/YYYY-MM-DD_HHMMSS/
On first run, WhisperX / pyannote may download model files. ownscribe shows a Preparing models step and best-effort download progress in the TUI while this happens.
ownscribe --mic # capture system audio + default mic (press 'm' to mute/unmute)
ownscribe --mic-device "MacBook Pro Microphone" # capture system audio + specific mic
ownscribe --device "MacBook Pro Microphone" # use mic instead of system audio
ownscribe --no-summarize # skip LLM summarization
ownscribe --diarize # enable speaker identification
ownscribe --language en # set transcription language (default: auto-detect)
ownscribe --model large-v3 # use a larger Whisper model
ownscribe --format json # output as JSON instead of markdown
ownscribe --no-keep-recording # auto-delete WAV files after transcription
ownscribe --template lecture # use the lecture summarization templateownscribe devices # list audio devices (uses native CoreAudio when available)
ownscribe apps # list running apps with PIDs for use with --pid
ownscribe warmup # prefetch WhisperX/pyannote models before a meeting
ownscribe transcribe recording.wav # transcribe an audio file (saves alongside the input)
ownscribe summarize transcript.md # summarize a transcript (saves alongside the input)
ownscribe resume ./2026-02-20_1736 # resume a failed/partial pipeline in a directory
ownscribe ask "question" # search your meetings with a natural-language question
ownscribe config # open config file in $EDITOR
ownscribe cleanup # remove ownscribe data from diskUse warmup ahead of time to avoid first-run model download delays while recording:
ownscribe warmup # prefetch Whisper model (+ diarization if enabled in config)
ownscribe warmup --language en # also prefetch alignment model for English
ownscribe warmup --with-diarization # force diarization warmup for this runUse ask to search across all your meeting notes with natural-language questions:
ownscribe ask "What did Anna say about the deadline?"
ownscribe ask "budget decisions" --since 2026-01-01
ownscribe ask "action items from last week" --limit 5This runs a two-stage pipeline:
- Find — sends meeting summaries to the LLM to identify which meetings are relevant
- Answer — sends the full transcripts of relevant meetings to the LLM to produce an answer with quotes
If the LLM finds no relevant meetings, a keyword fallback searches summaries and transcripts directly.
Config is stored at ~/.config/ownscribe/config.toml. Run ownscribe config to create and edit it.
[audio]
backend = "coreaudio" # "coreaudio" or "sounddevice"
device = "" # empty = system audio
mic = false # also capture microphone input
mic_device = "" # specific mic device name (empty = default)
[transcription]
model = "base" # tiny, base, small, medium, large-v3
language = "" # empty = auto-detect
[diarization]
enabled = false
hf_token = "" # HuggingFace token for pyannote
telemetry = false # allow HuggingFace Hub + pyannote metrics telemetry
device = "auto" # "auto" (mps if available), "mps", or "cpu"
[summarization]
enabled = true
backend = "ollama" # "ollama" or "openai"
model = "mistral"
host = "http://localhost:11434"
# template = "meeting" # "meeting", "lecture", "brief", or a custom name
# context_size = 0 # 0 = auto-detect from model; set manually for OpenAI-compatible backends
# Custom templates (optional):
# [templates.my-standup]
# system_prompt = "You summarize daily standups."
# prompt = "List each person's update:\n{transcript}"
[output]
dir = "~/ownscribe"
format = "markdown" # "markdown" or "json"
keep_recording = true # false = auto-delete WAV after transcriptionPrecedence: CLI flags > environment variables (HF_TOKEN, OLLAMA_HOST) > config file > defaults.
Built-in templates control how transcripts are summarized:
| Template | Best for | Output style |
|---|---|---|
meeting |
Meetings, standups, 1:1s | Summary, Key Points, Action Items, Decisions |
lecture |
Lectures, seminars, talks | Summary, Key Concepts, Key Takeaways |
brief |
Quick overviews | 3-5 bullet points |
Use --template on the CLI or set template in [summarization] config. Default is meeting.
Define custom templates in config:
[templates.my-standup]
system_prompt = "You summarize daily standups."
prompt = "List each person's update:\n{transcript}"Then use with --template my-standup or template = "my-standup" in config.
Speaker identification requires a HuggingFace token with access to the pyannote models:
- Accept the terms for both models on HuggingFace:
- Create a token at https://huggingface.co/settings/tokens
- Set
HF_TOKENenv var or addhf_tokento config - Run with
--diarize
On Apple Silicon Macs, diarization automatically uses the Metal Performance Shaders (MPS) GPU backend for ~10x faster processing. Set device = "cpu" in the [diarization] config section to disable this.
ownscribe builds on some excellent open-source projects:
- WhisperX — fast speech recognition with word-level timestamps and speaker diarization
- faster-whisper — CTranslate2-based Whisper inference
- pyannote.audio — speaker diarization
- Ollama — local LLM serving
- Click — CLI framework
See CONTRIBUTING.md for development setup, tests, and open contribution areas.
MIT