New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Audio To Text

by godot-fun in godot-fun/gai

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…

MITAuto-check passedAI & LLM Engineering

Install Audio To Text

skills CLI
$ npx skills add godot-fun/gai --skill audio-to-text -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install godot-fun/gai audio-to-text --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/godot-fun/gai.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/audio-to-text .claude/skills/audio-to-text && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
audio-to-text
GitHub stars
183
Token cost
~707 tokens
SKILL.md length
283 words
Files
1
Skills in repo
36
Repo updated
First seen
Licence
MIT

At a glance

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…

  • The user wants offline speech-to-text
  • SKILL.md covers Rules, Usage, Report and Troubleshooting
  • Calls python
  • Audio transcription

What it does

Audio To Text is an agent skill from godot-fun/gai. 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.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Transcription and Speech recognition and synthesis. It works with llama.cpp and Python. The repository describes itself as: A lightweight AI agent and skill workflow framework built with Godot. The licence is MIT.

When your agent uses it

  • The user wants offline speech-to-text
  • Audio transcription
  • Spoken-content extraction in Mandarin

Example prompts

  • “Use the audio-to-text skill to transcribe a single PCM16 WAV file to plain UTF-8 text locally through a standard-library Python wrapper around…”
  • “/audio-to-text”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 6394686. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Audio To Text loads about 707 tokens when it runs. Until then it costs about 114 tokens; SKILL.md has 283 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~114
When it runs · the whole SKILL.md, loaded when a task matches
~707

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from godot-fun/gai at commit 6394686, republished under its MIT licence (© godot-fun). 283 words, ~707 tokens.

Download SKILL.mdSave it as .claude/skills/audio-to-text/SKILL.md (or your agent's skills folder).
name
audio-to-text
description
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.

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 skill-dependency-manager before running commands.

  • Run .ai/audio-to-text/transcribe.py through the default python manifest entry. Do not invoke the native binary by hand.
  • Let the wrapper try funasr-llamacpp-gpu first with the Vulkan backend and fall back to funasr-llamacpp-cpu. Do not use CUDA, FunASR Python, PyTorch, ONNX, or host tools.
  • Load sensevoice-small-f16.gguf and fsmn-vad.gguf only from the sensevoice-small-gguf manifest 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 --vad for long-audio segmentation.
  • Produce plain UTF-8 transcription text only.
  • Never overwrite or modify the source audio.

Usage

Plain transcription:

powershell
.dependency/python/python.exe .ai/audio-to-text/transcribe.py --audio C:\path\speech.wav

Do 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 --cpu to 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.exe and the CPU runtime exist.
  • Missing model: verify both GGUF files exist under .dependency/sensevoice-small-gguf/model/.

© godot-fun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/audio-to-text of godot-fun/gai.

Open the folder on GitHubat commit 6394686

Compare with similar skills

Audio To Text next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Audio To Text compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audio To Text this skillgodot-fun/gai183—~707Automated safety check: PassMIT
Deepgram Audio Intelligence for Pythondeepgram/deepgram-python-sdk469—~2.3kAutomated safety check: PassMIT
Whisper Speech RecognitionOrchestra-Research/AI-Research-SKILLs13k7 repos~1.9kAutomated safety check: NotesMIT
Deepgram Flux Conversational STTdeepgram/deepgram-python-sdk469—~1.8kAutomated safety check: PassMIT
Verifylkmeta/txtify135—~583Automated safety check: PassApache-2.0
Watchmathiaschu/watch142—~4kAutomated safety check: WarnMIT

Similar skills

  • Deepgram Audio Intelligence for Python

    deepgram/deepgram-python-sdk

    Shows how to add Deepgram analytics such as diarization, summaries, sentiment, topics, redaction and language detection to speech transcription in Python.

    469 GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Whisper Speech Recognition

    Orchestra-Research/AI-Research-SKILLs

    Transcribes audio with OpenAI's Whisper: 99 languages, translation to English, language detection, six model sizes and word-level timestamps, from Python or the CLI.

    13k GitHub starsUsed in 7 repos~1.9k tokens
    AI & LLM EngineeringAuto-check: notes

  • Deepgram Flux Conversational STT

    deepgram/deepgram-python-sdk

    Writes and reviews Python code for Deepgram's turn-aware streaming speech-to-text (Flux, /v2/listen), including end-of-turn detection.

    469 GitHub stars~1.8k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Verify

    lkmeta/txtify

    Verify a Txtify change end-to-end. An agent skill from lkmeta/txtify.

    135 GitHub stars~583 tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed

  • Watch

    mathiaschu/watch

    Watch a video from YouTube, Instagram, X/Twitter, Vimeo, TikTok or any of ~1800 yt-dlp sites (or a local path).

    142 GitHub stars~4k tokensUpdated 4 mo ago
    Media & CreativeAuto-check: warnings

  • Azure Speech To Text REST Py

    microsoft/skills

    Official

    Azure Speech to Text REST API for short audio (Python). An agent skill from microsoft/skills.

    3.1k GitHub starsUsed in 5 repos~3k tokens
    Media & CreativeAuto-check passed

More from godot-fun/gai

All 36 skills in this repo

  • AI Text To Speech

    godot-fun/gai

    Zero-shot text-to-speech with voice cloning via IndexTTS2 (index-tts).

    183 GitHub stars~2k tokensUpdated today
    Auto-check passed

  • Audio Denoise

    godot-fun/gai

    Reduces background noise in a single audio file using FFmpeg afftdn.

    183 GitHub stars~465 tokensUpdated today
    Auto-check passed

  • Audio Fade

    godot-fun/gai

    Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg.

    183 GitHub stars~652 tokensUpdated today
    Auto-check passed

  • Audio Loudness Normalization

    godot-fun/gai

    Normalizes a single audio file to consistent LUFS loudness with true-peak limiting using FFmpeg.

    183 GitHub stars~684 tokensUpdated today
    Auto-check passed

  • Audio Sample Rate Standardize

    godot-fun/gai

    Standardizes a single audio file to 44100 or 48000 Hz and exports 16-bit PCM WAV using FFmpeg.

    183 GitHub stars~638 tokensUpdated today
    Auto-check passed

  • Audio Split

    godot-fun/gai

    Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg.

    183 GitHub stars~554 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Audio To Text

What does Audio To Text do?

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…. Audio To Text is an agent skill from godot-fun/gai.cpp runtimes, preferring cross-vendor Vulkan GPU acceleration and automatically falling back to CPU, with built-in FSMN-VAD.

When should I use Audio To Text?

Audio To Text fits situations like: the user wants offline speech-to-text; audio transcription; spoken-content extraction in Mandarin.

How do I install Audio To Text in Claude Code?

Run `npx skills add godot-fun/gai --skill audio-to-text -a claude-code`. Or copy the skill folder (.agents/skills/audio-to-text in godot-fun/gai) into .claude/skills/audio-to-text in your project. Claude Code loads it when a task matches its description.

How do I install Audio To Text in Codex?

Run `npx skills add godot-fun/gai --skill audio-to-text -a codex`. Or copy the skill folder (.agents/skills/audio-to-text in godot-fun/gai) into .agents/skills/audio-to-text in your project. Codex loads it when a task matches its description.

Can I use Audio To Text in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add godot-fun/gai --skill audio-to-text -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audio-to-text, .gemini/skills/audio-to-text, .github/skills/audio-to-text and .opencode/skills/audio-to-text in your project.

What does Audio To Text need to run?

Going by SKILL.md and its folder, Audio To Text needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Audio To Text access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Audio To Text safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audio To Text use?

Audio To Text is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audio To Text use?

About 707 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Audio To Text?

Skills that share tags, products or a category with Audio To Text: Deepgram Audio Intelligence for Python (deepgram/deepgram-python-sdk, 469 stars), Whisper Speech Recognition (Orchestra-Research/AI-Research-SKILLs, 13k stars), Deepgram Flux Conversational STT (deepgram/deepgram-python-sdk, 469 stars) and Verify (lkmeta/txtify, 135 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audio To Text?

godot-fun (a GitHub organization) maintains it in godot-fun/gai, which has 183 GitHub stars. The repository holds 36 skills in this directory. The repository was last updated on October 10, 2026.

Source: godot-fun/gai on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.