ModelsSelected

Qwen3 TTS 上线 Together AI,支持 9 种音色和 10 种语言

Why we picked it

阿里 Qwen 的语音合成模型登陆 Together AI,9 个音色能靠一句自然语言指令改语气,10 种语言共用同一个声音。做国际化应用、需要多语言配音的开发者可以直接在 Voicefinder 里拿自己的文本试听再接入,省掉不少调试时间。

Together AI 宣布 Qwen3 TTS 正式上线,提供 9 种预置音色供开发者选择。每种音色可以通过自然语言指令调整说话方式,例如改变语气或语速,无需额外微调。

Body

同一音色可在 10 种语言之间保持一致,适合多语言产品使用同一声音。这 9 种音色已同步接入 Together AI 的 Voicefinder,与平台上 850 多个其他音色并列展示。

开发者可以在 Voicefinder 中用自己的文本试听对比,再决定是否接入 API 写代码。Qwen3 TTS 来自阿里巴巴 Qwen 团队,此次通过 Together AI 进入欧美开发者渠道,与 ElevenLabs 等语音合成服务在多语言音色一致性上形成竞争。

Original · Together AI

qwen3 tts is now live on together ai

pick from 9 voices, change how they speak with a plain-language instruction, and keep the same voice across 10 languages

all 9 are now in voicefinder alongside 850+ other voices, so you can compare them on your own text before writing any code

https://t.co/XJN00mcBy8

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Qwen3, TTS, Together AI, speech synthesis.

Source attribution: curated from Together AI (@togethercompute).