MMaudio v2 produces synchronized audio from video or text inputs, ideal for adding soundtracks to videos when paired with video models. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.001per run·~1000 / $1
ExamplesView all
Shot in extreme macro perspective, a glowing, heat-rippled, and semi-translucent molten lava cube rests on a heatproof obsidian slab bathed in soft amber light. The camera gently pushes and pulls, catching the flickering embers and red-orange flows within its semi-liquid core. The angle shifts from overhead to a low 45-degree view, freezing the instant a tungsten blade presses into the lava, causing a soft sizzle and a split of glowing fissures. Each slice releases a bubbling hiss, subtle pops of heat pressure, and the low grind of metal through dense magma. These sizzling textures blend into a warm, immersive ASMR soundscape. The pacing remains unhurried, offering a hypnotic sensory experience.
Dog in stak board
A rugged male secret agent in a torn tactical suit sprints through a war-torn urban alley, pistol in one hand, a bleeding gash on his brow. His eyes are sharp and calculating, sweat glistening on his tense face. Explosions light up the background as he dives into cover in slow motion
Indian holy music
The sound of flames burning, explosions, screams.
ASMR-style soundscape. Intense, textured chewing and crunching sounds, like biting through thick, crystallized candy or hard caramel, mixed with subtle sizzling and bubbling lava ambiance. Occasional crackling pops, as if heat is escaping from the molten food. No speaking or human vocalizations.
Two boxers sparring, boxing sounds, cheering all around
A woman walking on a rainy night, footsteps, the clatter of rain
The sound of the waves, the sound of the violent winds
The peaceful atmosphere, the sound of the wind blowing the leaves, the chirping of birds
Related Models
README
MMAudio v2 — wavespeed-ai/mmaudio-v2
MMAudio v2 generates high-quality sound effects and ambience for a video using the visual content plus a text prompt. Upload a clip, describe the audio you want (environment, materials, impacts, whooshes, texture), and the model synthesizes a synced audio track that matches motion and timing. It’s ideal for adding cinematic SFX, atmospheric layers, and “sound design” style audio to silent footage.
Key capabilities
- Video-to-audio generation (adds sound to an existing video)
- Prompt-driven sound design: ambience, impacts, textures, mechanical sounds, nature
- Timing-aware audio that follows visual motion beats
- Optional negative_prompt to avoid unwanted audio characteristics
- Duration control for generating audio for different clip lengths
- mask_away_clip option for generating audio without directly using the original clip audio
Use cases
- Add cinematic ambience to silent clips (city night, wind, rain, room tone)
- Create synced sound effects (footsteps, fabric rustle, metal clanks, sparks)
- Product and food sound design (sizzles, pours, crackles, knife cuts)
- Trailer-style audio layers for short edits and social videos
- Rapid sound prototyping before final mix and mastering
Pricing
| Unit | Price |
|---|---|
| Per second of audio | $0.001 |
Examples:
| Duration | Price |
|---|---|
| 5s | $0.005 |
| 8s | $0.008 |
| 10s | $0.010 |
Inputs
- video (required): the source video to generate audio for
- prompt (required): describe the desired sound
Parameters
- duration: audio length in seconds
- num_inference_steps: sampling steps
- guidance_scale: prompt adherence strength
- negative_prompt: what to avoid (e.g., “muffled, noisy, distorted, music”)
- mask_away_clip: whether to mask away the clip (useful when you want fully generated audio)
Prompting guide (video → audio)
Write prompts like a sound designer:
- Environment: location + ambience (rainy alley, factory hall, forest dawn)
- Materials: metal, glass, lava, fabric, wood, water
- Actions: slice, pour, crackle, hiss, whoosh, impact
- Texture: crisp, gritty, low rumble, sparkling high-end, subtle room tone
- Timing beats: “as the blade presses in…”, “when the cube hits the ground…”
Example prompts
- A glowing lava cube crackles and pops with ember flickers. A tungsten blade presses into the semi-liquid core with a soft sizzling hiss, tiny molten droplets splatter, low rumble underneath, cinematic close-mic detail.
- Rainy city night ambience with distant traffic, soft wind, occasional footsteps, subtle neon buzz, realistic stereo space.
Mmaudio v2 API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2 with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Mmaudio v2 below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"negative_prompt": "blurry, low quality, distorted",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/mmaudio-v2", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"negative_prompt": "blurry, low quality, distorted",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/mmaudio-v2",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://example.com/your-input.mp4",
"negative_prompt": "blurry, low quality, distorted",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": false
}
)
print(output["outputs"][0]) # → URL of the generated outputMmaudio v2 API — Frequently asked questions
What is the Mmaudio v2 API?
Mmaudio v2 is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. MMaudio v2 produces synchronized audio from video or text inputs, ideal for adding soundtracks to videos when paired with video models. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Mmaudio v2 API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/mmaudio-v2.
How much does Mmaudio v2 cost per run?
Mmaudio v2 starts at $0.001 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Mmaudio v2 accept?
Key inputs: `prompt`, `video`, `duration`, `guidance_scale`, `num_inference_steps`, `negative_prompt`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/mmaudio-v2.
How long does Mmaudio v2 take to generate?
Average end-to-end generation time on WaveSpeedAI is around 20 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Mmaudio v2 outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.