venice-audio-music
Skill2 starsChanged 5 months agoMITView on GitHub
Async music / audio-track generation via Venice. Covers the /audio/quote + /audio/queue + /audio/retrieve + /audio/complete lifecycle, lyrics vs instrumental, voice selection, duration, language, speed, model capability probing, and webhook-free polling.
- Reads credentials
- Sends data out
4 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
- jhy0285/monofieldtheir own version, first seen Oct 13, 2026
- veniceai/skillsedited, first seen Oct 13, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- veniceai/skills★ 17116% same
Wrote their own version · 3
- jhy0285/monofield★ 6same name
- jpoindexter/theft-kit★ 1same name
- davidanthonyn/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 repository19 other files it gives its agents.
- cheaptokensSkill
- venice-api-keysSkill
- venice-api-overviewSkill
- venice-audio-speechSkill
- venice-audio-transcriptionSkill
- venice-augmentSkill
- venice-authSkill
- venice-billingSkill
- venice-charactersSkill
- venice-chatSkill
- venice-crypto-rpcSkill
- venice-embeddingsSkill
- venice-errorsSkill
- venice-image-editSkill
- venice-image-generateSkill
- venice-modelsSkill
- venice-responsesSkill
- venice-videoSkill
- venice-x402Skill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 90
If still processing: JSON {"status":"PROCESSING","average_execution_time":...,"execution_duration":...}.
- Very specific: line 91
If done: binary audio body (audio/mpeg or similar).
- Very specific: line 162
Before calling /audio/queue, inspect the model entry returned by GET /models?type=music — each row's model_spec exposes (among other …
≈ “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
Venice Music / Async Audio
Music (and long-form voice) generation is asynchronous. The flow is:
POST /api/v1/audio/quote → price in USD
POST /api/v1/audio/queue → { queue_id } (funds reserved)
POST /api/v1/audio/retrieve → status or binary audio
POST /api/v1/audio/complete → finalize & delete mediaFor short text-to-speech, use the synchronous venice-audio-speech endpoint instead.
Use when
- You need songs, jingles, score, soundscape, or long narration.
- The selected model uses duration-based or character-based pricing and must be priced before submission.
- The expected generation time is long enough (> 20 s) that sync call would time out.
Lifecycle
1. POST /audio/quote — price it first
curl https://api.venice.ai/api/v1/audio/quote \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs-music",
"duration_seconds": 60
}'Response: {"quote": 0.48} (USD).
| Field | Notes |
model | Required. Music/audio model from GET /models?type=music. |
duration_seconds | Integer or numeric string. Only if the model reports duration metadata. |
character_count | Required for models with pricing.per_thousand_characters (long narration). |
2. POST /audio/queue — enqueue
curl https://api.venice.ai/api/v1/audio/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs-music",
"prompt": "Uplifting indie-folk acoustic track, 120 BPM, major key.",
"lyrics_prompt": "Verse 1: Walking through the city lights...\nChorus: We are the dreamers...",
"duration_seconds": 60,
"voice": "Aria",
"language_code": "en",
"speed": 1.0,
"force_instrumental": false,
"lyrics_optimizer": false
}'Response: { "model": "...", "queue_id": "uuid" }.
| Field | Notes |
model | Required. |
prompt | Required. Describe genre, mood, tempo, instruments. Length caps in /models. |
lyrics_prompt | Lyrics. Required when lyrics_required=true, rejected when supports_lyrics=false. |
duration_seconds | Integer or string. Model-dependent. |
force_instrumental | Only when supports_force_instrumental=true. |
lyrics_optimizer | Auto-generate lyrics from prompt. Requires supports_lyrics_optimizer=true. lyrics_prompt must be empty. |
voice | For voice-enabled models. See voices + default_voice in /models. |
language_code | ISO 639-1. Requires supports_language_code=true. |
speed | Requires supports_speed=true. Use model's min_speed/max_speed. |
3. POST /audio/retrieve — poll status / download
curl https://api.venice.ai/api/v1/audio/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"elevenlabs-music","queue_id":"..."}' \
--output track.mp3- If still processing: JSON
{"status":"PROCESSING","average_execution_time":...,"execution_duration":...}. - If done: binary audio body (
audio/mpegor similar). Save the bytes. - Set
delete_media_on_completion: trueto skip step 4.
Poll every 2–5 s; use average_execution_time (ms, P80) as a guideline for your first poll delay.
4. POST /audio/complete — cleanup
curl https://api.venice.ai/api/v1/audio/complete \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"elevenlabs-music","queue_id":"..."}'Removes the media from Venice storage after you've downloaded it. Required unless you used delete_media_on_completion: true on retrieve.
Full loop (TypeScript)
const base = 'https://api.venice.ai/api/v1'
const headers = {
Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
'Content-Type': 'application/json',
}
async function generateTrack() {
// 1. Quote
const quote = await fetch(`${base}/audio/quote`, {
method: 'POST', headers,
body: JSON.stringify({ model: 'elevenlabs-music', duration_seconds: 60 }),
}).then(r => r.json())
console.log('price:', quote.quote)
// 2. Queue
const { queue_id, model } = await fetch(`${base}/audio/queue`, {
method: 'POST', headers,
body: JSON.stringify({
model: 'elevenlabs-music',
prompt: 'Uplifting indie-folk acoustic track, 120 BPM.',
duration_seconds: 60,
force_instrumental: true,
}),
}).then(r => r.json())
// 3. Poll
while (true) {
const res = await fetch(`${base}/audio/retrieve`, {
method: 'POST', headers,
body: JSON.stringify({ model, queue_id }),
})
const ct = res.headers.get('content-type') ?? ''
if (ct.startsWith('audio/')) {
const buf = Buffer.from(await res.arrayBuffer())
await fs.writeFile('track.mp3', buf)
break
}
const { status } = await res.json()
if (status !== 'PROCESSING') throw new Error(`unexpected ${status}`)
await new Promise(r => setTimeout(r, 3000))
}
// 4. Complete
await fetch(`${base}/audio/complete`, {
method: 'POST', headers,
body: JSON.stringify({ model, queue_id }),
})
}Capability probing
Before calling /audio/queue, inspect the model entry returned by GET /models?type=music — each row's model_spec exposes (among other fields):
supports_lyrics,lyrics_required,supports_lyrics_optimizersupports_force_instrumental,supports_speed,supports_language_codevoices[],default_voicemin_prompt_length,prompt_character_limitmin_speed,max_speedpricing.generation(per-job),pricing.per_second(per second generated),pricing.per_thousand_characters(character-priced narration), orpricing.durations(duration-tiered map:{ "<tier>": { usd, diem, min_seconds, max_seconds } }) — each model uses one of these shapes
Errors
| Code | Meaning |
400 | Wrong params (lyrics on an instrumental-only model, duration_seconds outside allowed range, voice not in model's list). |
401 | Auth / Pro-only model. |
402 | Insufficient balance. Bearer → INSUFFICIENT_BALANCE; x402 → PAYMENT_REQUIRED. |
404 | On retrieve/complete: unknown / expired queue_id. |
422 | Content policy violation. ContentViolationError may include suggested_prompt. |
429 | Rate limited. |
500 / 503 | Inference or capacity issue. |
Gotchas
- Quote before queue — music is pay-per-second; unexpected
duration_secondscan blow through a budget. Use/audio/quoteto gate thequeuecall against your available balance (/billing/balanceor/x402/balance/...). queue_idis UUIDv4. Store it alongside themodel— both are required for every subsequent call.- Media URLs are ephemeral. Download during
retrieveand store yourself; aftercomplete, Venice deletes the file. lyrics_optimizer: trueand a non-emptylyrics_promptis a400.- Poll rate: don't hammer
/retrieve. 2–5 s is plenty — the job queue is the same regardless of poll frequency. execution_durationfrom the retrieve status is cumulative (ms since enqueue);average_execution_timeis the P80 expected total.
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.

