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
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
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.
| Unit | Price |
|---|---|
| Per second of audio | $0.001 |
Examples:
| Duration | Price |
|---|---|
| 5s | $0.005 |
| 8s | $0.008 |
| 10s | $0.010 |
Write prompts like a sound designer:
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Mmaudio v2 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": false
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"num_inference_steps": 25,
"duration": 8,
"guidance_scale": 4.5,
"mask_away_clip": False
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/mmaudio-v2", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)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.
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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/mmaudio-v2.
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.
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.
Median end-to-end generation time on WaveSpeedAI is around 11 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.