CosyVoice-V2vsspeech-2.8-hd
Both text to speech models, compared at each maker’s own API list prices. Every figure links to its source.
Key differences
Max input
20,000 Alibaba Cloud Model Studio: CosyVoice WebSocket client events · as of Nov 2, 2026
10,000 MiniMax API: T2A (HTTP) · as of Nov 2, 2026
CharacterMaker’s official API · china · CNY
¥2.00 / 10K characters 阿里云百炼：模型价格in Chinese · as of Nov 2, 2026
¥3.50 / 10K characters MiniMax 按量计费价格in Chinese · as of Nov 1, 2026
These differences use verified vendor specifications or each maker’s official API on the same region, currency, meter and billing conditions. Different conditions remain side by side in the full table; they do not establish which model is cheaper. Declared features describe support, not measured quality or a recommendation. Missing evidence does not mean a feature is unsupported.
Full comparison
| CosyVoice-V2 Alibaba Qwen | speech-2.8-hd MiniMax | |
|---|---|---|
| Overview | ||
| Released | May 27, 2025 | Jan 23, 2026 |
| Specs | ||
| Languages | Not stated | 40 |
| Voices | 70 | Not stated |
| Voice cloning | Not stated | |
| Streaming | ||
| Max input | 20,000 | 10,000 |
| Pricing | ||
| Price per 1M characters | ¥200.00 | $100.00 |
Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.
Model details and sources
- CosyVoice-V2 → Available
- speech-2.8-hd → Available