audio-to-text
Skill210 starsChanged 2 days agoMITView on GitHub
Transcribes a single PCM16 WAV file to plain UTF-8 text locally through a standard-library Python wrapper around native SenseVoice Small F16 GGUF FunASR llama.cpp runtimes, preferring cross-vendor Vulkan GPU acceleration and automatically falling back to CPU, with built-in FSMN-VAD. Use when the user wants offline speech-to-text, audio transcription, ASR, or spoken-content extraction in Mandarin, Cantonese, English, Japanese, or Korean.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- godot-fun/gaiword for word, first seen Nov 15, 2026
- sulaksh555/claude-skillstheir own version, first seen Oct 20, 2026
- cyberstarlab/skillstheir own version, first seen Mar 2, 2026
- lucas-acc/sancho-skillstheir own version, first seen Feb 8, 2026
Other versions4 projects use a version of this.
Word for word · 1
- godot-fun/gai★ 210100% same
Edited · 0
None found.
Wrote their own version · 3
- lucas-acc/sancho-skills★ 14same name
- cyberstarlab/skills★ 1same name
- sulaksh555/claude-skills★ 0same name
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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .agents/skills/AGENTS.mdAGENTS.md
- ai-text-to-speechSkill
- audio-denoiseSkill
- audio-fadeSkill
- audio-loudness-normalizationSkill
- audio-sample-rate-standardizeSkill
- audio-splitSkill
- audio-to-oggSkill
- audio-to-wavSkill
- audio-trimSkill
- audio-volume-adjustSkill
- file-naming-normalizationSkill
- git-commit-messageSkill
- image-inpaint-regionSkill
- image-region-remove-key-color-appSkill
- image-remove-backgroundSkill
- image-remove-white-backgroundSkill
- image-resizeSkill
- image-sprite-sheet-splitSkill
- image-to-pngSkill
- image-to-textSkill
- image-trimSkill
- storyboard-av-mixSkill
- storyboard-shot-to-htmlSkill
- storyboardSkill
- storyboard-ttsSkill
- video-4k-normalizationSkill
- video-bgmSkill
- video-compress-to-sizeSkill
- video-cutSkill
- video-merge-gpuSkill
- video-mergeSkill
- video-publishSkill
- video-remove-audioSkill
- video-to-4kSkill
- video-to-60fpsSkill
- video-to-mp4Skill
- video-to-ogvSkill
- video-to-wavSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Read and follow dependency-manager before running commands.
- Very specific: line 14
Run .ai/audio-to-text/transcribe.py through the default python manifest entry.
- Very specific: line 19
Always pass --vad for long-audio segmentation.
- Distinctive: line 21
Never overwrite or modify the source audio.
- Distinctive: line 31
Do not write a transcript file.
- Very specific: line 33
Use --cpu only when the user explicitly requests CPU or Vulkan troubleshooting requires bypassing GPU acceleration.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Audio to Text
Run the bundled standard-library Python wrapper, which validates input, invokes native llama-funasr-sensevoice, removes runtime logs, and prints only UTF-8 transcription text. Prefer the Vulkan runtime for NVIDIA, AMD, or Intel GPUs and automatically retry with CPU when Vulkan is unavailable. Do not use CUDA, PyTorch, FunASR Python, or a remote API.
Rules
Read and follow dependency-manager before running commands.
- Run
.ai/audio-to-text/transcribe.pythrough the defaultpythonmanifest entry. Do not invoke the native binary by hand. - Let the wrapper try
funasr-llamacpp-gpufirst with the Vulkan backend and fall back tofunasr-llamacpp-cpu. Do not use CUDA, FunASR Python, PyTorch, ONNX, or host tools. - Load
sensevoice-small-f16.ggufandfsmn-vad.ggufonly from thesensevoice-small-ggufmanifest model directory. - Process exactly one audio file per invocation. Repeat the command for multiple files.
- Require uncompressed PCM16 WAV input. The current native runtime accepts common sample rates and channel layouts. For other containers, first chain
audio-to-wav. - Always pass
--vadfor long-audio segmentation. - Produce plain UTF-8 transcription text only.
- Never overwrite or modify the source audio.
Usage
Plain transcription:
.dependency/python/python.exe .ai/audio-to-text/transcribe.py --audio C:\path\speech.wavDo not write a transcript file. Return the text printed to stdout. See cli/audio-to-text.md for tests and copy-paste commands.
Use --cpu only when the user explicitly requests CPU or Vulkan troubleshooting requires bypassing GPU acceleration.
Report
Return only the transcript. For long audio, summarize instead of dumping the entire transcript unless asked.
Troubleshooting
- Invalid WAV: convert to uncompressed PCM16 WAV before retrying.
- Vulkan fallback: update the GPU driver and confirm it exposes a Vulkan device; use
--cputo bypass Vulkan deliberately. - Slow inference: F16 prioritizes fidelity and uses more memory than Q8.
- Missing runtime: verify both
.dependency/funasr-llamacpp-gpu/llama-funasr-sensevoice.exeand the CPU runtime exist. - Missing model: verify both GGUF files exist under
.dependency/sensevoice-small-gguf/model/.
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.

