voice-to-text
Skill1 starsChanged 9 months agoMITView on GitHub
Transcribe audio/video files to text with speaker identification. Use when the user mentions "transcribe," "transcription," "voice to text," "audio to text," "meeting notes," "interview transcript," "diarize," "speaker identification," or provides an audio/video file path and wants it converted to text.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- pengasuzie/claude-skillsword for word, first seen Mar 2, 2026
Other versions1 project uses a version of this.
Word for word · 1
- pengasuzie/claude-skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- competitive-intelSkill
- competitor-landscapeSkill
- due-diligenceSkill
- market-researchSkill
- new-ideaSkill
- opportunity-briefSkill
- strategic-analysisSkill
- strategy-sessionSkill
- text-to-voiceSkill
- viability-assessmentSkill
- voice-briefingSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 5 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
whisperX: must be installed globally via pipx: pipx install "whisperx @ git+https://github.com/m-bain/whisperX.git" --python python3.13
- Very specific: line 13
Hugging Face token: must be saved at ~/.cache/huggingface/token (for pyannote speaker diarization)
- Very specific: line 20
If the user hasn't provided a file path, first check ~/Downloads/ for the most recently added .m4a file using:
- Very specific: line 26
If a file is found, show the filename and ask the user to confirm it's the right one before proceeding.
- Distinctive: line 32
Ask only if not obvious from context:
- Very specific: line 54
Always use --compute_type int8 on Mac (float16 is not supported on CPU)
- Very specific: line 55
Always set TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 (PyTorch 2.6+ compatibility with pyannote)
- Distinctive: line 62
Read the output file
- Very specific: line 64
If speaker labels are generic (SPEAKER_00, SPEAKER_01), ask the user if they want to replace them with real names
- Distinctive: line 68
If the user wants cleaner output, offer to:
- Distinctive: line 74
After the transcript is ready, ask:
- Very specific: line 78
If the user says yes, invoke the voice-briefing skill with the transcript file path.
- Distinctive: line 92
If the user just wants plain transcription (no speaker identification), drop the diarize flags:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Voice to Text
You are a transcription assistant. Your job is to transcribe audio and video files into clean, readable text with speaker identification using whisperX.
Prerequisites
- whisperX must be installed globally via pipx:
pipx install "whisperx @ git+https://github.com/m-bain/whisperX.git" --python python3.13 - Hugging Face token must be saved at
~/.cache/huggingface/token(for pyannote speaker diarization) - pyannote model access must be accepted at: https://huggingface.co/pyannote/speaker-diarization-3.1 and https://huggingface.co/pyannote/segmentation-3.0
When Invoked
Step 1: Get the audio file path
If the user hasn't provided a file path, first check ~/Downloads/ for the most recently added .m4a file using:
ls -t ~/Downloads/*.m4a 2>/dev/null | head -1If a file is found, show the filename and ask the user to confirm it's the right one before proceeding. If no .m4a is found in Downloads, or the user says it's not the right file, ask them for the path.
Supported formats: .m4a, .mp3, .wav, .flac, .ogg, .webm, .mp4, .mkv, .avi
Step 2: Determine parameters
Ask only if not obvious from context:
| Parameter | Default | When to ask |
| Number of speakers | 2 | If unclear (e.g., meeting vs interview vs monologue) |
| Language | en | If file might not be English |
| Output directory | Current project's docs/private/ | If user wants it elsewhere |
| Output format | txt | If user wants srt, vtt, json, or all |
Step 3: Run transcription
TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 whisperx "<file_path>" \
--diarize \
--min_speakers <N> --max_speakers <N> \
--language <lang> \
--compute_type int8 \
--output_dir "<output_dir>" \
--output_format <format>Important notes:
- Always use
--compute_type int8on Mac (float16 is not supported on CPU) - Always set
TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1(PyTorch 2.6+ compatibility with pyannote) - First run downloads ~360MB model; subsequent runs are fast
- Transcription of a 30-min file takes roughly 3-5 minutes on Mac
Step 4: Review output
After transcription completes:
- Read the output file
- Report: number of lines, speakers identified, any notable issues
- If speaker labels are generic (SPEAKER_00, SPEAKER_01), ask the user if they want to replace them with real names
Step 5: Optional cleanup
If the user wants cleaner output, offer to:
- Replace speaker labels with real names (e.g., SPEAKER_00 → Bruce, SPEAKER_01 → Aaron)
- Add timestamps (use
--output_format allto get timestamped formats)
Step 6: Offer voice-briefing
After the transcript is ready, ask:
"Transcript is ready. Want me to run
/voice-briefingon it to write it up as a business analysis in the context of everything else I know about your project and the market, and produce an mp3 reading of it and drop it in your dropbox folder?"
If the user says yes, invoke the voice-briefing skill with the transcript file path.
Troubleshooting
| Error | Fix |
float16 compute type not supported | Use --compute_type int8 |
UnpicklingError: Weights only load failed | Set TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 |
No --hf_token provided | Run: ~/.local/pipx/venvs/whisperx/bin/huggingface-cli login --token <TOKEN> |
401 Unauthorized for pyannote | Accept model terms on HuggingFace (links in Prerequisites) |
whisperx: command not found | Install: pipx install "whisperx @ git+https://github.com/m-bain/whisperX.git" --python python3.13 |
Without Speaker Diarization
If the user just wants plain transcription (no speaker identification), drop the diarize flags:
TORCH_FORCE_NO_WEIGHTS_ONLY_LOAD=1 whisperx "<file_path>" \
--language <lang> \
--compute_type int8 \
--output_dir "<output_dir>" \
--output_format <format>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

