VOD AIGC Update: EL compose v2.5 Music Generation and sound_t2s_v3 Sound Effect Generation Models Released
VOD AIGC adds three versions to the EL (ElevenLabs) model (released 2026-11-16). The action is still CreateAigcAudioTask; SceneType is not specified.
| ModelName | ModelVersion | Purpose | Key capabilities |
|---|---|---|---|
EL | compose_v2.5 | Music | Prompt to music |
EL | compose_detailed_v2.5 | Music | Prompt to music (ElevenLabs "Compose music with details" endpoint) |
EL | sound_t2s_v3 | Sound effects | Text to sound effect |
1. Music: compose v2.5
- Use
compose_v2.5for general music generation; the existingcompose_v2remains available. OutputConfig.Durationdoes not apply to thecompose_*music versions.- ⚠️ Whether
compose_detailed_v2.5accepts acomposition_plan(section-level structure) and returns extra metadata is not yet confirmed.
2. Sound effects: sound_t2s_v3
- For short sound effects, the latest
sound_t2s_v3is recommended; the existingsound_t2s_v2remains available. sound_t2s_v3takes the same parameters assound_t2s_v2. Set the length withOutputConfig.Duration(seconds,[1, 30]).- To migrate an existing v2 request, just change
ModelVersiontosound_t2s_v3.