All models
Qwen
Qwen Audio 3.0 TTS Flash
Fast speech synthesis, two voices
This model is not in the catalog right now.
See available modelsAbout the model
Qwen Audio 3.0 TTS Flash turns text into speech: you send text and get back sound. Unlike voice conversation partners, it reads what you send rather than replying to it. The smaller model in the line and cheaper than the larger one, it is the choice for volume: notifications, assistant replies, short messages. Speech models are billed per character, not per token.
Strengths
- Reads the text you send rather than replying to it
- Two voices to choose from
- Cheaper than the larger model in the line
- Billed per character
Where to use it
- Voicing notifications
- Assistant voice replies
- Short messages at volume