Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yaoapp/yao-audio
Audio expert. ALWAYS invoke this skill when the user asks to transcribe, recognize, or convert speech/audio to text.
Passed 11 of 15 test cases with the skill, and 6 of 15 without it.
and 9 more in the full report
10 fixed7 passed either way4 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Transcribe the audio file /notes/dictation_ja.wav with the spoken language set to Japanese.
| Checked | Without skill | With skill |
|---|---|---|
| Passes ja to the language parameter | Missed | Passed |
The instructions your model reads when the skill loads.
Use these tools to transcribe audio files to text using speech-to-text models.
Transcribe an audio file to text.
tai tool audio_transcribe --audio_path /path/to/meeting.m4a
tai tool audio_transcribe --audio_path /path/to/recording.wav --language en --provider llm.my-openai:whisper-1
| Parameter | Type | Required | Description |
|---|---|---|---|
| audio_path | string | yes | Audio file path. Supported: mp3, m4a, wav, webm, mp4, mpeg, mpga |
| language | string | no | ISO 639-1 language code (e.g. en, zh, ja). Auto-detected if omitted |
| provider | string | no | STT provider connector ID. If omitted, uses the default STT provider |
List available speech-to-text providers and models.
tai tool audio_providers
| Parameter | Type | Required | Description |
|---|---|---|---|
| capability | string | no | Filter by capability (default: audio) |
Returns a list of providers with their available models and connector IDs that can be passed to audio_transcribe.
Only use the parameters listed above for each tool. Do not pass unsupported parameters — they will be ignored or cause errors.
test cases passed, vs 6 / 15 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.