Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.
MiniMax音频生成发布日期 2026年8月13日原生推理新Generates complete stereo songs from lyrics and a style prompt, with duration, seed, and format controls up to 5 minutes.
也称为 MiniMax-Music3
minimax-music-3/v1/audio/generationsminimax-music3minimax-music3.0minimax/music3minimax/minimax-music3minimaxai/minimax-music3MiniMax-Music3来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。
MiniMax Music 3 通过 POST /v1/audio/generations 运行。请求会立即返回 job_id；轮询 GET /v1/jobs/{job_id} 直到任务完成，再从结果中读取输出 URL。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/audio/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-music-3",
"prompt": "Describe what you want MiniMax Music 3 to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/audio/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "minimax-music-3",
"prompt": "Describe what you want MiniMax Music 3 to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)EmpirioLabs 上 MiniMax Music 3 API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| prompt | string | - | - | Style and arrangement instructions for MiniMax Music 3. Describe genre, mood, vocal character, and instrumentation. |
| lyrics | string | - | - | Song lyrics. Required for a vocal track. Hidden when Instrumental is on. Put one structure tag on its own line before each section. Supported tags: [Intro], [Verse],... |
| instrumental | boolean | true | - | When on, the model writes an instrumental track and lyrics stay hidden. Turn this off to write a vocal song. |
| audio_duration | number | 10 | 10 到 300 | Length of the generated song in seconds. MiniMax Music 3 accepts 10 to 300 seconds and bills a 10 second minimum. |
| seed | integer | - | - | Random seed for reproducibility. Same seed and identical params produce the same song. |
| format | enum | wav | wav, flac, mp3 | Audio container format. WAV is uncompressed, FLAC is lossless, MP3 is a smaller file. |
| response_format | enum | url | url, b64_json | How the worker returns the audio. url returns a signed URL; b64_json inlines the bytes. |
| return_base64 | boolean | false | - | When true, the response includes the rendered audio as base64. |
Supports prompt (style and arrangement), lyrics with structure tags, instrumental mode, 10-300s duration, seed, and WAV, FLAC, or MP3 output. URL or base64 response format.
在 EmpirioLabs，MiniMax Music 3 按量计费。本页的实时价格表始终与 API 的实际计费一致。
MiniMax Music 3 通过 api.empiriolabs.ai 上的 POST /v1/audio/generations 提供，使用标准的 Bearer 令牌认证。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 MiniMax Music 3，你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。
