Fish Audio Drama3Preview
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- Ant Group open-sources Ming-3.0-tts, tops two open-source TTS leaderboards
Ant Group has released Ming-3.0-tts, an open-source text-to-speech model whose weights are published on Hugging Face under the MIT license, according to AIbase AI新闻. The release includes a 0.5B dense model and a 7.9B mixture-of-experts variant called Ming-3.0-tts-tiny, and the model offers preset voices plus stateless voice cloning. AIbase, citing Artificial Analysis leaderboards, reports that Ming-3.0-tts scored 93.2% on pronunciation robustness to tie for first among 31 models ahead of Eleven v4 at 91.7%, ranked first among open-source models in the Controlled Voice Arena with a 1,069 Elo over 1,827 evaluations and 13th overall, and placed third among open-source models in Provider Voice with 1,188 Elo over 1,957 evaluations and 19th overall.
AIbase AI新闻 · 🔥 0
Experience and discussion from the community
Share my Fish Audio Drama3Preview experienceAsk about Fish Audio Drama3Preview
Nobody has shared their experience with Fish Audio Drama3Preview yet.