MMAudio V2
Generate synchronized audio and sound effects from text prompts with MMAudio V2.
Price
$0.0552
per minute of audio
Length
1s–0.5m
Lyrics
No
Instrumental
—
Pricing
USD per minute of audio$0.0009 per second of generated audio.
Specs
- Model ID
mmaudio-v2-text-to-audio- Endpoint
POST /api/v1/audio/queue- Duration
- 1–30 seconds (default 5)
- Lyrics
- Not supported
- Formats
- wav
- Prompt limit
- 500 characters
- Added
- Feb 28, 2026
POST
/api/v1/audio/queue# 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.mp3Privacy
Tier 1 · this model
Anonymized
Venice hides your identity and stores no prompts. MMAudio still sees the content.
Tier 2
Private
Not available
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available