Create a music or sound generation task

Music and audio generation submission API, compatible with the legacy /suno/submit/music path. Returns a task ID, which can later be queried through /suno/fetch/{task_id}.

Music and audio generation task submission API. The path remains /suno/submit/music, and you can choose the generation engine via upstream_model, music_model, engine, model_id, or modelId. The create API returns task_id, which can then be used to query the output through /suno/fetch/{task_id}.

If upstream_model is not provided (or only {"model":"suno_music"} is provided), Suno v5.5 is used by default. To continue using the legacy Suno version, explicitly pass "upstream_model":"suno-v5".

New models

Prompt Description Mode

Suitable for describing only the style, mood, language, singer type, and scenario, with the model automatically generating the song content.

{
  "model": "suno_music",
  "upstream_model": "suno-v5.5",
  "prompt": "Create an energetic retro-pop DJ song about the artificial intelligence revolution.",
  "make_instrumental": false
}

Audio generation

MiniMax Speech can override voice parameters via extraParams (or top-level same-name snake_case/camelCase fields).

{
  "model": "suno_music",
  "upstream_model": "minimax-speech-2.8-hd",
  "prompt": "欢迎使用新版语音生成服务。",
  "extraParams": {
    "voice": "moss_audio_ce44fc67-7ce3-11f0-8de5-96e35d26fb85",
    "outputFormat": "mp3",
    "sampleRate": 32000,
    "speed": 1,
    "volume": 1,
    "pitch": 0
  }
}

When no voice parameters are provided for MiniMax Speech, the server sends voice, outputFormat=mp3, sampleRate=32000, speed=1, volume=1, and pitch=0 from the example above by default.

Lyria 3 Pro uses upstream_model=lyria-3-pro (or lyria-3-pro-preview):

{
  "model": "suno_music",
  "upstream_model": "lyria-3-pro",
  "prompt": "Cinematic orchestral music with a hopeful finale."
}

Light Music or Instrumental Only

You can use light_music=true or make_instrumental=true. light_music indicates a preference for light music/background music, and make_instrumental indicates that no sung vocals will be generated.

{
  "model": "suno_music",
  "upstream_model": "minimax-music-v2.6",
  "prompt": "Warm cafe background music with soft piano and strings, relaxing and cinematic.",
  "light_music": true,
  "make_instrumental": true
}

Advanced Lyrics Mode

Suitable when the business side has already prepared the lyrics and needs to specify the title and style tags. custom_mode=true can be passed, and the lyrics field can use lyrics, lyric, custom_lyrics, or customLyrics.

{
  "model": "suno_music",
  "upstream_model": "mureka-v9",
  "custom_mode": true,
  "title": "Summer Sea Breeze",
  "tags": "electro pop, female vocal, bright summer",
  "lyrics": "[Verse]\nSea breeze moves across the white sand\n[Chorus]\nTurn the summer into a beam of light"
}

Query

After creation succeeds, save the returned data task ID, such as task_xxx, and call GET /suno/fetch/{task_id} to query the status, audio URL, cover, title, lyrics, and the upstream raw fragment information.