Chinese text-to-speech models convert scripts into audio. Compare preset voices, voice control, cloning support and access paths using each exact model's documentation. Character, audio and compute billing are separate from chat-model token pricing.
| Model | Creator | Context | Open weight | Tags |
|---|---|---|---|---|
| Qwen3 TTS 1.7B CustomVoice | Alibaba | Not applicable | Yes | text-to-speech · tts |
| Realtime-Venus-Audio | Ant Group | 41K | Yes | audio_understanding · full_duplex · text-to-speech |
| Realtime-Venus-Omni | Ant Group | 41K | Yes | multimodal · vision · full_duplex |
| MiniMax Speech 2.8 HD | MiniMax | Not applicable | — | text-to-speech · tts |
| MiniMax Speech 2.8 TURBO | MiniMax | Not applicable | — | text-to-speech · tts |
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.