AI news
公司内部站点 · 页面资源保存在本地（2026-10-17 14:56 UTC）· 独立 X 采集尚未配置；互动计数仅限本站

Four labs lead open-weight TTS across nine language leaderboards

Artificial Analysis

Artificial Analysis reports that no single open-weight text-to-speech model leads all nine new language leaderboards, with four labs ahead in different languages.

Boson AI’s Higgs Audio V3 TTS is the top open-weight model in Hindi, German, Portuguese and Vietnamese. FishAudio’s OpenAudio S1 Mini leads the open-weight field in Japanese, Spanish and Arabic. MistralAI’s Voxtral TTS leads in French, and BreezeBlue’s Breeze TTS 2 leads in Mandarin.

Open-weight coverage is thinner than the full public field: each language leaderboard ranks 2 to 6 open-weight models, compared with 15 to 24 public models overall.

#text-to-speech#open-weights#benchmarks#multilingual#artificial-analysis

Artificial Analysis adds TTS leaderboards for nine languages

Artificial Analysis has extended the Controlled Voice Arena with separate text-to-speech leaderboards for Japanese, Mandarin Chinese, Hindi, Spanish, German, French, Portuguese, Vietnamese, and Arabic. Rankings use native-language prompts, standardized cloned voices, and preference votes from first-language speakers.