Together AI adds Qwen3 TTS for real-time voice at 97ms to first audio
Together AI has made Qwen3 TTS, Qwen's open text-to-speech model, available on its serverless inference platform and dedicated endpoints, the company says. It costs $20 per million characters, and Together says its inference team tuned the serving stack so first audio arrives in as little as 97 milliseconds, with HTTP streaming and a WebSocket API for real-time voice applications.
The model separates who is speaking from how they speak: developers pick one of nine preset voices and change its tone with a plain-language instruction such as "excited and upbeat," and each voice speaks 10 languages including Chinese, English, Japanese, German and Spanish. Qwen recommends using a voice in its native language for the best quality, Together notes. Futurum says the addition makes Together a more credible full-stack inference provider for voice agents.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
Salesforce releases SOV-Transcribe-1, an open-weight speech-to-text model
OpenAI Opens Decisions API to All Customers
Quiq brings its voice AI agent to the Zoom App Marketplace
Alibaba launches Qwen4-Max, a closed 2.4-trillion-parameter flagship model
Liquid AI releases LiquidCodec, an open 74M-parameter streaming speech codec
Daily AI Brief: the AI news that matters, in your inbox.