music-1.5

🎯 Supported music generation models for invocation

📝 Description of the music, used to specify style, mood and scene.
Example: “Pop music, sad, suitable for rainy nights”
Restriction Notes:

1. music-2.5 model: Optional, length limit [0, 2000] characters
2. Non-music-2.5 models: Required, length limit [10, 2000] characters

📜 Lyrics of the song, with the following relevant specifications:

1. Line Separation: Use \n to separate each line of lyrics
2. Structure Optimization: Structural tags such as [Intro], [Verse], [Pre Chorus], [Chorus], [Interlude], [Bridge], [Outro], [Post Chorus], [Transition], [Break], [Hook], [Build Up], [Inst], [Solo] can be added to optimize the structure of the generated music
3. Length Limit:
   • music-2.5 model: [1, 3500] characters
   • Non-music-2.5 models: [10, 3500] characters

⚡ Whether to enable streaming return, default value: false

📤 Return format of the audio, with the following relevant instructions:

1. Optional values: url or hex, default value: hex
2. Special Restriction: When stream is true, only hex format is supported
3. Supplementary Tip: The validity period of the url is 24 hours, please download the corresponding audio file in a timely manner

🔧 Audio generation configuration items, used to customize the basic parameters of the audio

🏷️ Add AIGC audio rhythm watermark at the end, relevant restriction: Only effective for non-streaming return, default value: Disabled (false)