Qwen3 TTS lands on Together AI: 9 voices, 10 languages, first audio in 97ms

togethercompute · x · 2026-11-21

Qwen3 TTS is now live on Together AI's Serverless Inference and dedicated endpoints at $20 per 1M characters. The open model separates who speaks from how they speak: 9 preset voices whose tone and emotion can be changed mid-stream via plain-language instructions like "excited and upbeat," with each voice staying consistent across 10 languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, Italian). First audio arrives in as little as 97ms, with HTTP streaming and a WebSocket API for incremental text. All 9 voices are in VoiceFinder alongside 850+ others for side-by-side comparison on your own text.

Related event: Qwen3 TTS Lands on Together AI with 9 Voices and 10 Languages(2 posts)→

Original post →

More from Multimodal

Multimodal channel →