XiaomiMiMo/MiMo-V2.5-tts-voicedesign
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. Automatically generate voices from text descriptions, without requiring presets or audio samples.
Try the model with a sample request using the same API shape shown in the reference page.
Natural language description of the desired voice (gender/age, texture, mood, speech speed). See the MiMo-V2.5-TTS-VoiceDesign documentation for guidance on writing effective descriptions.
Text to convert to speech. Should match the tone described by `voice`.
Whether to stream the output.
Select the desired format for the speech output. Supported formats include mp3, opus, flac, wav, and pcm.
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.
