PulseAugur
EN
LIVE 20:17:14

Together AI launches Qwen3 TTS with real-time, multilingual voice customization

Together AI has launched Qwen3 TTS, an open-source text-to-speech model, offering developers advanced voice customization and multilingual capabilities. The model allows users to select from nine preset voices and modify their tone and emotion through simple text instructions, supporting ten languages including Chinese, English, Japanese, and German. Qwen3 TTS is optimized for real-time applications, delivering the first audio output in as little as 97 milliseconds and supporting HTTP streaming and WebSocket APIs for continuous speech generation. AI

IMPACT Enables developers to integrate highly customizable, multilingual speech synthesis into applications with low latency.

RANK_REASON Product launch of a specific model on a platform, not a frontier release from a major lab.

Read on Together AI blog →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Together AI launches Qwen3 TTS with real-time, multilingual voice customization

How we ranked this

Signal score
2 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Product launch of a specific model on a platform, not a frontier release from a major lab.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Together AI blog TIER_1 English(EN) ·

    Qwen3 TTS is now available on Together AI

    Qwen3 TTS is now available on Together AI. Keep one voice across your product, change its tone with a plain-language instruction and move it between 10 languages, with first audio in as little as 97ms.