XiaomiMiMo/MiMo-V2.5-tts
Automatically convert input text into natural and fluent speech output. You can generate natural and vivid speech content by configuring parameters such as speech style and voice. Use the high-quality voices from the built-in voices list.
Try the model with a sample request using the same API shape shown in the reference page.
Text to convert to speech. May contain (style) and [audio tag] controls — e.g. "(Lazy)Let me sleep five more minutes..." or "(Sighing)I miss those days." See the MiMo-V2.5-TTS docs for the full tag list.
Optional natural language instruction describing the desired speaking style, emotion, role-play, dialect, etc. Sent in the `user` role; not synthesized.. (Default: empty)
Whether to stream the output. The MiMo-V2.5-TTS streaming API is currently downgraded to compatibility mode and returns the full audio after generation finishes.
Select the desired format for the speech output. Supported formats include mp3, opus, flac, wav, and pcm.
Built-in voice name for MiMo-V2.5-TTS speech synthesis.
The service tier used for processing the request. When set to 'priority', the request will be processed with higher priority (only applies to models that support it).
Adjust settings and run the demo to see the model output generated here in real-time.
