compose_detailed_stream
Generate and stream custom music from text prompts or composition plans, returning detailed audio responses. Requires ElevenLabs credits.
Instructions
Stream Composed Music With A Detailed Response Spends ElevenLabs credits.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| seed | No | ||
| prompt | No | ||
| model_id | No | ||
| finetune_id | No | ||
| lyrics_text | No | ||
| music_prompt | No | Composition plan for the `music_v1` model. Using this field with any other model will result in an error. | |
| output_format | No | Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Use "auto" (the default) to let the API pick the best format for the selected model: mp3_44100_128 for v1 models and mp3_48000_192 for v2 models. | |
| generation_mode | No | ||
| music_length_ms | No | ||
| with_timestamps | No | Whether to return the timestamps of the words in the generated song. | |
| composition_plan | No | ||
| finetune_strength | No | How strongly the finetune influences the generation. Defaults to 1.0 (full strength). Lower values soften the influence of the finetune, leaving more room for prompt-level steering. Only meaningful when `finetune_id` is also provided. | |
| force_instrumental | No | If true, guarantees that the generated song will be instrumental. If false, the song may or may not be instrumental depending on the `prompt`. Can only be used with `prompt`. | |
| use_phonetic_names | No | If true, proper names in the prompt will be phonetically spelled in the lyrics for better pronunciation by the music model. The original names will be restored in word timestamps. | |
| store_for_inpainting | No | Whether to store the generated song for inpainting. | |
| with_waveform_visual | No | Whether to return the visual waveform of the generated song. |