MiniMax Music 2.6 generates complete songs with vocals and instrumentals from text prompts and lyrics. Supports instrumental-only mode, auto lyrics generation, structure tags for song arrangement, and configurable audio quality. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.15per run·~66 / $10
dark cyberpunk synthwave, pulsing bass, neon-soaked atmosphere, dystopian future vibes, aggressive electronic beats, 808 drums, layered synth arpeggios, BPM 128
warm acoustic folk, fingerpicked guitar, soft female vocal, cozy afternoon feeling, gentle reverb, intimate recording, storytelling mood, BPM 72
MiniMax Music 2.6 generates complete songs with vocals and instrumentals from a text prompt and lyrics. Describe the genre, mood, instruments, and tempo — the model composes and sings a full track with your lyrics, with support for structure tags, instrumental-only mode, auto lyrics generation, and configurable audio quality up to 256kbps/44.1kHz.
Complete song generation Produces full vocal and instrumental tracks from a single prompt and lyrics input — not just clips or loops.
Structure tag support Use tags like [Verse], [Chorus], [Bridge], and more in your lyrics to precisely control song arrangement and flow.
Auto lyrics generation Leave the lyrics field empty and the model will generate lyrics automatically from your prompt description.
Instrumental mode Enable is_instrumental to generate a backing track without any vocals — ideal for music beds, soundtracks, and production use.
Configurable audio quality Adjust bitrate (up to 256kbps) and sample rate (up to 44.1kHz) to match your delivery requirements.
Wide genre support Pop, rock, folk, electronic, orchestral, lo-fi, and more — all controllable through your prompt.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Music style description including genre, mood, instruments, and tempo. Max 2000 characters. |
| lyrics | Yes | Song lyrics with optional structure tags. 10–3000 characters. Leave empty for auto-generation. |
| bitrate | No | Audio bitrate: 32000, 60000, 64000, 128000, or 256000 (default). |
| sample_rate | No | Audio sample rate: 16000, 24000, 32000, or 44100 (default). |
| is_instrumental | No | Generate instrumental music without vocals. Default: off. |
Use these tags in your lyrics to control song arrangement:
[Intro], [Verse], [Pre Chorus], [Chorus], [Post Chorus], [Interlude], [Bridge], [Outro], [Hook], [Build Up], [Break], [Transition], [Inst], [Solo]
warm acoustic folk, fingerpicked guitar, soft female vocal, cozy afternoon feeling, gentle reverb, intimate recording, storytelling mood, BPM 72
[Verse] Sunlight through the window pane Coffee getting cold again
[Chorus] Time moves slow on days like these Carried softly by the breeze
Just $0.15 per song (up to 5 minutes).
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/music-2.6 with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Music 2.6 below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"bitrate": 256000,
"sample_rate": 44100,
"is_instrumental": false
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/minimax/music-2.6" \
-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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/minimax/music-2.6";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"bitrate": 256000,
"sample_rate": 44100,
"is_instrumental": false
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
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",
"bitrate": 256000,
"sample_rate": 44100,
"is_instrumental": 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/minimax/music-2.6", 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 = 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", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Music 2.6 is a MiniMax model for music generation, exposed as a REST API on WaveSpeedAI. MiniMax Music 2.6 generates complete songs with vocals and instrumentals from text prompts and lyrics. Supports instrumental-only mode, auto lyrics generation, structure tags for song arrangement, and configurable audio quality. 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/music-2.6.
Music 2.6 starts at $0.15 per run or per second. 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`, `bitrate`, `is_instrumental`, `lyrics`, `sample_rate`. 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/minimax/music-2.6.
Reported generation time on WaveSpeedAI is around 81 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (MiniMax). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.