Skip to main content
POST
/
audio
/
queue
/api/v1/audio/queue
curl --request POST \
  --url https://api.venice.ai/api/v1/audio/queue \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "elevenlabs-music",
  "prompt": "A warm spoken narration introducing a product launch.",
  "lyrics_prompt": "Verse 1: Walking through the city lights...",
  "duration_seconds": 60,
  "force_instrumental": false,
  "voice": "Aria",
  "speed": 1
}
'
{
  "model": "elevenlabs-music",
  "queue_id": "123e4567-e89b-12d3-a456-426614174000",
  "status": "QUEUED"
}
Call /audio/quote to estimate cost, then poll /audio/retrieve with the returned queue_id until the generation finishes. If you keep generated media after retrieval, call /audio/complete once you have downloaded it.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
model
string
required

The model to use for audio generation.

Example:

"elevenlabs-music"

​
prompt
string
required

The prompt describing the audio to generate. Minimum and maximum prompt lengths vary by model; inspect /models for min_prompt_length and prompt_character_limit.

Minimum string length: 1
Example:

"A warm spoken narration introducing a product launch."

​
lyrics_prompt
string

Optional lyrics/text for lyric-capable models. Required when /models reports lyrics_required=true; unsupported when /models reports supports_lyrics=false.

Example:

"Verse 1: Walking through the city lights..."

​
duration_seconds

Optional duration hint in seconds. Only supported for models that expose duration metadata via /models. Accepts either an integer or a numeric string. If omitted, the model default duration is used when available.

Required range: x > 0
Example:

60

​
force_instrumental
boolean

Optional instrumental toggle. Only supported when /models reports supports_force_instrumental=true.

Example:

false

​
voice
string

Optional voice selection for voice-enabled models. See /models?type=music for the model's supported voices and default_voice.

Example:

"Aria"

​
speed
number

Optional audio speed multiplier. Only supported when /models reports supports_speed=true; use the model-specific min_speed and max_speed values.

Required range: 0.25 <= x <= 4
Example:

1

Response

Audio generation request queued successfully

​
model
string
required

The ID of the model used for audio generation.

Example:

"elevenlabs-music"

​
queue_id
string
required

The ID of the audio generation request. Use this to poll for status and retrieve the result.

Example:

"123e4567-e89b-12d3-a456-426614174000"

​
status
enum<string>
required

The status of the audio generation request.

Available options:
QUEUED
Example:

"QUEUED"