asr transcribe to text

Other Community

Skill notes

Step 0: Detect Platform and Load Config

If config exists, read values and proceed to Step 1. If config does not exist, auto-detect platform first: Then use AskUserQuestion with platform-aware defaults: For macOS Apple Silicon (recommended: local): For other platforms (recommended: remote):

Step 1: Resolve Input

Accept local files, direct media URLs, or web/podcast episode pages. Web or podcast page URL: inspect the page for an existing transcript first.

Step 2: Extract Audio (if input is video)

For video files (mp4, mov, mkv, avi, webm), extract as 16kHz mono WAV: Audio files (wav, mp3, m4a, flac, ogg) can be used directly. Get duration: Cleanup: After transcription succeeds, delete extracted WAV files to save disk space.

Preprocess: Merge Segments & Shrink Metered Uploads (optional)

Run this BEFORE transcription when either applies: The recording is a multi-segment dump — body mics and field recorders split sessions into fixed-length files (e.g. TX02_MIC024_....wav, TX02_MIC025_....wav; TX01/TX02 = DJI MIC MINI 2S internal recording — device roster and the recorder→Feishu-Minutes paths: the meeting-ingest skill's meeting-ingest/references/architecture.md §①-L0).

Path A: Local MLX (macOS Apple Silicon) — default

Run the decoupled speaker pipeline — it handles dependency pins, model loading, and the critical max_tokens parameter internally. Expected output (per file): Outputs per input: <stem>.txt ([MM:SS - MM:SS] SPEAKER_xx + text), <stem>.csv (file,start,end,duration,speaker,text — feeds review UIs and

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Other
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@daymade · no license declared
Token usage
Heavy
Setup complexity
Manual integration
External API key
Required · Vendor-specific
Operating systems
macOS · Windows · WSL · Docker
Runtime requirements
Docker
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
External requests
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Output preview asr-transcribe-to-text.preview
# Step 4: Verify Output

Transcription may be truncated:
- Expected: ~[N] chars for [M] minutes of audio
- Got: [actual] chars ([pct]% of expected)
- Last line: "[last 100 chars...]"

Options:
A) Retry with higher max_tokens (current: [N], try: [N*2])
B) Switch mode — try [local/remote] instead
C) Save as-is — the output looks complete to me
D) Abort

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.