Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/listen
Nested swiss-knife reference for local audio analysis — transcribe speech with Whisper, or extract musical features (tempo, key, dynamics, spectral profile) with librosa. Both run on the user's machine with no API key. Read this when the human asks you to transcribe a voice note, extract lyrics from singing, critique generated music, or analyze audio characteristics. For *creating* music or audio, use the sibling `minimax-cli` reference (or `dj` for journal-inspired music) instead.
Passed 17 of 20 test cases with the skill, and 10 of 20 without it.
and 6 more in the full report
9 fixed10 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which field in the music analysis JSON document measures the 85th-percentile frequency boundary representing where high-frequency energy ends?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies `spectral_rolloff_hz` as the 85th-percentile frequency boundary | Missed | Passed |
The instructions your model reads when the skill loads.
Nested swiss-knife reference for local-only audio analysis. No API key, no network. Two actions: transcribe (speech → text) or appreciate (music → numerical critique).
| Action | Backend | When |
|---|---|---|
| transcribe | faster-whisper (local Whisper) | Spoken word, voice notes, podcasts, lectures. Works on singing too but lyrics may be inaccurate. |
| appreciate | librosa (signal processing) | Music — tempo, key, frequency bands, dynamics. Returns numerical measurements, not subjective descriptions. |
Both actions are wrappers around the bundled scripts. Run them with bash like any other command-line tool:
python3 <skill-path>/scripts/transcribe.py <audio-file>
python3 <skill-path>/scripts/appreciate.py <audio-file>
The scripts auto-install their dependencies via lingtai.venv_resolve.ensure_package on first run, so the first invocation may take ~30 s.
python3 <skill-path>/scripts/transcribe.py <audio-path> [--model base] [--device cpu]
| Flag | Default | Notes |
|---|---|---|
--model | base | Whisper model size: tiny, base, small, medium, large-v2, large-v3. Larger = more accurate, slower, more RAM. |
--device | cpu | Use cuda if you have a GPU. |
--compute-type | int8 | CTranslate2 compute type. int8 is the fastest CPU mode. Use float16 on GPU. |
Output: a JSON document on stdout with:
{
"text": "<full transcript>",
"language": "en",
"language_probability": 0.99,
"duration": 42.3,
test cases passed, vs 10 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.