Together AI (model by Qwen) · Hosted TTS

Qwen3 TTS on Together AI

Together AI now hosts Qwen3 TTS, Qwen's open text-to-speech model, on Serverless Inference and dedicated endpoints at $20 per 1M characters. The model offers nine preset voices, each speaking 10 languages, with a plain-language instruction controlling delivery, and first audio in as little as 97ms with HTTP and WebSocket streaming. Access is through the Together Python SDK and VoiceFinder.

Open the source ↗

Similar Audio & Speech releases

  • Sophon-Realtime v1

    Adventists AI · Full-Duplex Voice · Week 47, 2026

  • Eleven v4 and v4 Turbo

    ElevenLabs · Expressive TTS Model · Week 41, 2026

  • Maya1

    Maya Research · Text-to-Speech · Week 31, 2026

  • Speech-to-Speech

    Hugging Face · Voice Agents · Week 31, 2026

  • Gradium

    Gradium (Kyutai spin-out, Paris) · Voice Agents · Week 30, 2026

  • Miso-TTS

    Miso Labs · Text-to-Speech · Week 24, 2026

Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.