music_generation
Generate AI music from text prompts and lyrics. Create custom audio tracks by describing style, mood, or scenes and providing song lyrics for musical composition.
Instructions
Create a music generation task using AI models. Generate music from prompt and lyrics.
COST WARNING: This tool makes an API call to Minimax which may incur costs. Only use when explicitly requested by the user.
Args:
prompt (str): Music creation inspiration describing style, mood, scene, etc.
Example: "Pop music, sad, suitable for rainy nights". Character range: [10, 300]
lyrics (str): Song lyrics for music generation.
Use newline (\n) to separate each line of lyrics. Supports lyric structure tags [Intro][Verse][Chorus][Bridge][Outro]
to enhance musicality. Character range: [10, 600] (each Chinese character, punctuation, and letter counts as 1 character)
stream (bool, optional): Whether to enable streaming mode. Defaults to False
sample_rate (int, optional): Sample rate of generated music. Values: [16000, 24000, 32000, 44100]
bitrate (int, optional): Bitrate of generated music. Values: [32000, 64000, 128000, 256000]
format (str, optional): Format of generated music. Values: ["mp3", "wav", "pcm"]. Defaults to "mp3"
output_directory (str, optional): Directory to save the generated music file
Note: Currently supports generating music up to 1 minute in length.
Returns:
Text content with the path to the generated music file or generation status.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| lyrics | Yes | ||
| sample_rate | No | ||
| bitrate | No | ||
| format | No | mp3 | |
| output_directory | No |