u2-tts
Unisound's speech synthesis model with streaming (sub-90 ms first packet) and async long-text modes, 12 languages plus Cantonese and Sichuanese, and pronunciation tags.
01 Price
¥200.00per 1M chars
¥2 per 10,000 characters of input text.
Pricing source, checked 2026-11-18
02 Languages 12
03 Features 3 of 8 listed
- Emotion control
- Voice cloningnot listed
- Voice designnot listed
- SSMLnot listed
- Phoneme input
- Speed / prosody control
- Style controlnot listed
- Multi-speakernot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/unisound/models/u2-tts
Free, no key needed. Use model id u2-tts with Unisound (云知声)'s own API. API reference.