Convert audio files to text accurately using Qwen3 speech recognition models.

Install

mkdir -p .claude/skills/skills-second-state && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10964" && unzip -o skill.zip -d .claude/skills/skills-second-state && rm skill.zip

Installs to .claude/skills/skills-second-state

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Transcribe speech from audio files to text.
43 chars · catalog descriptionno explicit “when” trigger
Beginner

Key capabilities

  • Transcribes audio files to text
  • Supports multiple audio formats
  • Uses Qwen3-ASR model
  • Prints transcription to stdout

How it works

It utilizes the Qwen3-ASR model to process audio files and output the recognized speech as text.

Inputs & outputs

You give it
Audio file path
You get back
Transcribed text

When to use skills

  • Transcribing recorded interviews
  • Converting audio meeting notes to text
  • Processing media files for documentation

About this skill

Qwen3 ASR — Voice Transcription

Transcribe speech from audio files to text.

Binary

  • {baseDir}/scripts/asr — Speech-to-text transcription.

Models

  • {baseDir}/scripts/models/Qwen3-ASR-0.6B — Speech recognition model (0.6B parameters).

Transcription

Transcribe an audio file to text.

{baseDir}/scripts/asr \
  {baseDir}/scripts/models/Qwen3-ASR-0.6B \
  <audio_file>

Parameters

ParameterRequiredDescription
model_pathYesPath to the model directory (0.6B or 1.7B)
audio_fileYesPath to the audio file (any FFmpeg-supported format)

Output

Prints the transcribed text to standard output.

Example

{baseDir}/scripts/asr \
  {baseDir}/scripts/models/Qwen3-ASR-0.6B \
  recording.wav

Supported Audio Formats

Any format supported by FFmpeg: WAV, MP3, M4A, FLAC, OGG, and more. Audio is automatically resampled to 16 kHz mono internally.

Workflow

1. Identify the Audio File

Get the path to the audio file the user wants to transcribe.

2. Run the Command

Run the asr binary with the full paths to the binary and model directory.

{baseDir}/scripts/asr \
  {baseDir}/scripts/models/Qwen3-ASR-0.6B \
  /path/to/audio.wav

3. Return the Transcription

The transcribed text is printed to stdout. Return it to the user.

When not to use it

  • When the audio file is not supported by FFmpeg
  • When the user needs real-time transcription

Limitations

  • Requires model files
  • Offline processing only

How it compares

It provides a dedicated CLI tool for offline, model-based transcription.

Compared to similar skills

skills side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
skills (this skill)05moReviewBeginner
hugging-face-evaluation02moReviewIntermediate
Create SDRF06moReviewBeginner
report-research16moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry