Fish Audio Drama 3 is live on TapNow from day zero.
Shape emotion, cue whispers and laughs, and control delivery with text instructions.
Clearer pronunciation of rare English words, numbers, and technical terms.
From narration to character dialogue.
Fish Audio has released Drama 3, an open-weight text-to-speech model that accepts performance directions within the text.
→ The model uses a 35-billion-parameter mixture-of-experts design with about 3 billion parameters active per token
→ It supports up to 16 speakers in a single text and 83 languages
→ Fish Audio reports a 93.2% score on Artificial Analysis' pronunciation robustness benchmark
→ The weights are available on Hugging Face under a Fish Audio license
Source: