--- name: speech115-transcribe description: "Transcribe local audio/video and YouTube media with local FluidAudio/Parakeet, optional diarization, and standard transcript artifacts." license: "Apache-2.0" metadata: decimalai-skill-id: "11d1460b-7e84-4a18-a1f1-093e92ef4b27" decimalai-version-id: "17a54c8e-886b-46e8-bbdd-2d0ceeb5b127" decimalai-version: "2" decimalai-body-sha256: "80c2c021d99f27adbcc55e0bf4f3f69c52d33c04163946e4039b093ec92793f4" decimalai-name: "speech115/transcribe" decimalai-format: "1" decimalai-invocation: "model" decimalai-category: "documentation" decimalai-source: "https://app.decimal.ai/s/speech115-transcribe@2/SKILL.md" --- # Transcribe Use the installed CLI directly for private or routine media: ```bash transcribe --speakers auto ``` Invoke `transcribe` directly. Do not run it from a source checkout, set `PYTHONPATH`, or call `python -m transcribe`; if it is not on PATH, repair the installation first. Run `transcribe doctor` when installation health is unclear. Language and speaker count are automatic. Use `--lang`, `--speakers`, `--out` or `--out-root`, `--diar-mode`, and `--formats srt,vtt` when explicitly needed. When running with `--speakers auto`, the agent must allow the local FluidAudio process to read and write these paths; CoreML/E5RT diarization can fail inside a restricted sandbox otherwise: - `~/Library/Application Support/FluidAudio` - `~/Library/Caches/fluidaudiocli` Every run writes non-empty `transcript.md`, `transcript.json`, and `manifest.json`; subtitles are optional. Read `manifest.json` before reporting metrics, and read `transcript.md` only for follow-up semantic work. Keep private media local and never paste media, transcripts, or API keys into chat. Do not silently switch engines. MacWhisper is allowed only when the user explicitly requests it or approves it as a fallback after its doctor passes. For YouTube, use `yt-dlp` through the CLI. Existing finished transcripts should be processed directly rather than transcribed again.