Transcribe
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
What it does
Transcribe audio files to text using OpenAI models, with optional speaker diarization and known-speaker hints.
- Transcribe audio
- Diarize speakers
- Extract text
- Process recordings
Audio Transcribe
Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.
Workflow
- Collect inputs: audio file path(s), desired response format (text/json/diarized_json), optional language hint, and any known speaker references.
- Verify
OPENAI_API_KEYis set. If missing, ask the user to set it locally (do not ask them to paste the key). - Run the bundled
transcribe_diarize.pyCLI with sensible defaults (fast text transcription). - Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.
- Save outputs under
output/transcribe/when working in this repo.
Decision rules
- Default to
gpt-4o-mini-transcribewith--response-format textfor fast transcription. - If the user wants speaker labels or diarization, use
--model gpt-4o-transcribe-diarize --response-format diarized_json. - If audio is longer than ~30 seconds, keep
--chunking-strategy auto. - Prompting is not supported for
gpt-4o-transcribe-diarize.
Output conventions
- Use
output/transcribe/<job-id>/for evaluation runs. - Use
--out-dirfor multiple files to avoid overwriting.
Dependencies (install if missing)
Prefer uv for dependency management.
uv pip install openai
If uv is unavailable:
python3 -m pip install openai
Environment
OPENAI_API_KEYmust be set for live API calls.- If the key is missing, instruct the user to create one in the OpenAI platform UI and export it in their shell.
- Never ask the user to paste the full key in chat.
Skill path (set once)
export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export TRANSCRIBE_CLI="$CODEX_HOME/skills/transcribe/scripts/transcribe_diarize.py"User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).
CLI quick start
Single file (fast text default):
python3 "$TRANSCRIBE_CLI" \
path/to/audio.wav \
--out transcript.txt
Diarization with known speakers (up to 4):
python3 "$TRANSCRIBE_CLI" \
meeting.m4a \
--model gpt-4o-transcribe-diarize \
--known-speaker "Alice=refs/alice.wav" \
--known-speaker "Bob=refs/bob.wav" \
--response-format diarized_json \
--out-dir output/transcribe/meeting
Plain text output (explicit):
python3 "$TRANSCRIBE_CLI" \
interview.mp3 \
--response-format text \
--out interview.txt
Reference map
references/api.md: supported formats, limits, response formats, and known-speaker notes.
Developer & API
curl -sL https://agentvouch.xyz
/api/skills/d3f45ae6-357d-4b4d-a17c-989f8972c9d2/raw -o SKILL.mdGET /api/skills/d3f45ae6-357d-4b4d-a17c-989f8972c9d2/rawAuth: Authorization: Bearer sk_... or wallet signature. Get API key →
Mirrored from openai/skills