Audio Models and APIs

This series contains 13 models. Use the full model ID and follow its documentation for request formats and parameters. Checked on 2026-10-04; consult the console for current availability.

Model ID	API documentation
`mimo-v2.5-tts-voicedesign`	MiMo Speech Synthesis
`mimo-v2.5-tts-voiceclone`	MiMo Speech Synthesis
`mimo-v2.5-tts`	MiMo Speech Synthesis
`mimo-v2.5-asr`	MiMo Speech Recognition
`suno_wav`	Integration Guide
`suno_upload`	Integration Guide
`suno_timing`	Integration Guide
`suno_stem`	Integration Guide
`suno_lyrics`	Integration Guide
`suno_music`	Integration Guide
`qwen3-omni-flash-realtime`	Qwen Realtime Audio Protocols
`qwen3-tts-instruct-flash-realtime`	Qwen Realtime Audio Protocols
`qwen3.5-omni-flash-realtime`	Qwen Realtime Audio Protocols

All Models and APIs