Together AI Launches Qwen3 TTS Text-to-Speech Service
Together AI Blog says Qwen3 TTS is now available through Together Serverless Inference and dedicated endpoints at $20 per 1 million characters. The model offers nine preset voices, plain-language control of tone and emotion, and 10 languages, with HTTP and WebSocket streaming for real-time voice applications. Together AI reports first audio in as little as 97ms, while Qwen has released the 12Hz 1.7B model under the Apache 2.0 license.
The launch gives developers an open text-to-speech model with multilingual voices, controllable delivery, streaming APIs, and a published price for building real-time voice applications.
Summary
- Qwen3 TTS on Together AI: Qwen's open text-to-speech model, on Together Serverless Inference and dedicated endpoints at \$20 per 1M characters.
- One voice, many deliveries: nine preset voices that change tone and emotion from a plain-language instruction such as "excited and upbeat."
- 10 languages per voice: every preset speaks Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish and Italian.
- Built for real-time voice: first audio in as little as 97ms, with HTTP streaming and a WebSocket API for text that arrives in pieces.
Starting today, developers can run Qwen3 TTS on Together AI, with first audio in as little as 97ms.
Qwen3 TTS is an open text-to-speech model that separates who is speaking from how they speak. You choose one of nine preset voices, and that voice stays the same while you change its delivery with a plain-language instruction, such as "excited and upbeat," or move it between 10 languages.
Together AI's inference team tuned the serving stack for Qwen3 TTS so that speech starts streaming quickly enough for real-time conversation. The model is available now on Together Serverless Inference and on dedicated endpoints.
#Qwen3 TTS 12Hz 1.7B#Qwen#Together AI#Together Serverless Inference