MMAudio V2 API

MMAudio V2 is a sound effects model by MMAudio, available on the Venice API as mmaudio-v2-text-to-audio. Requests are anonymized, so the provider never sees your identity.Generate synchronized audio and sound effects from text prompts with MMAudio V2.

MMAudio V2 API pricing

Model ID	Variant	Privacy	Price
`mmaudio-v2-text-to-audio`	Standard	Anonymized	$0.06 per minute of audio

MMAudio V2 specifications

Spec	Value
Provider	MMAudio
Released	Feb 28, 2026
Privacy	Anonymized

How to use the MMAudio V2 API

Send requests to POST https://api.venice.ai/api/v1/audio/queue with "model": "mmaudio-v2-text-to-audio" and your API key.

# 1. Queue the job
curl https://api.venice.ai/api/v1/audio/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mmaudio-v2-text-to-audio",
    "prompt": "Heavy wooden door creaking open in a stone hallway",
    "duration_seconds": 5
  }'

# 2. Retrieve when ready
curl https://api.venice.ai/api/v1/audio/retrieve \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "mmaudio-v2-text-to-audio", "queue_id": "<queue_id>" }' --output audio.mp3

MMAudio V2 API FAQ

How much does the MMAudio V2 API cost?

$0.055 per minute of generated audio. Prices are in USD and can be paid in DIEM at parity.

What is the MMAudio V2 model ID?

Use mmaudio-v2-text-to-audio as the model parameter.

Is the MMAudio V2 API private?

MMAudio V2 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

Which endpoint does the MMAudio V2 API use?

Queue a job with POST /audio/queue, then poll /audio/retrieve for the result.

Related models

ElevenLabs Sound Effects API: $0.14 per minute of audio
Sonilo V1.1 Sound Effects API: $0.12 per minute of audio

Explore

By modality