Fish Audio releases Drama 3 text-to-speech model
MarkTechPost: Fish Audio Releases Drama 3, a 35B Open-Weight MoE Text-to-Speech Model
This week, Fish Audio released Fish Audio Drama 3. Drama 3 is a text-to-speech model from Fish Audio that takes plain-language acting direction. It is a 35B mixture-of-experts model with about 3B parameters active per token. The weights are on Hugging Face, and the model is also live in the Fish Audio API. For developers, it is a self-hostable option for scripted dialogue, audiobooks and dubbing. TL;DR Size: 35B total parameters, about 3B active per token (8 of 256 experts plus 1 shared)
Get smart on it
Fish Audio released Drama 3, a text-to-speech model that converts scripts with plain-language acting directions into spoken dialogue, supporting up to 16 characters per request across 83 languages. The model is open-weight with 35 billion total parameters but only about 3 billion active parameters per token, requiring at least 48 GB of NVIDIA GPU memory to self-host. Drama 3 achieves high accuracy on pronunciation benchmarks, scoring 93.2% overall on Artificial Analysis Pronunciation Robustness, though it performs less well on exact sequences like codes and emails. The model is available through a hosted API at a list price of $50 per million characters and is free for commercial use below $500,000 in annual revenue, making it accessible to developers working on scripted dialogue, audiobooks, and dubbing.
Explainer: What Is a Mixture of Experts Model and Why Does It Use Fewer Resources?
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Gemini 4 Argon: Built to solve your hardest problems
The new model aims to handle complex reasoning tasks where current systems often struggle or fail completely.
Also reported by The Verge, Ars Technica, The Decoder and SiliconANGLE
OpenAI will reportedly ship at least one model this year but its flagship still needs alignment work
OpenAI is racing to finish its next flagship model, which uses the same looped transformer technique as Astra to boost math and coding performance. The tradeoff is that looping makes safety monitoring harder. Microsoft accidentally revealed details about how the technique works on a public page. Whether or not the flagship is ready in time, employees say one or two new models will likely ship by year's end. The article OpenAI will reportedly ship at least one model this year but its fla
Meta releases its first frontier model, Muse Wonder
Meta's Superintelligence Lab released a pair of new state-of-the-art models on Monday, Muse Wonder and Muse Wonder Full, the company's first attempt at a frontier model.
Also reported by The Verge, Wired AI, The Decoder and SiliconANGLE
AI Came for Math. Now It’s Chasing the Rest of Science
AI may soon be the default way to solve theoretical problems in economics, high-energy physics, and other fields, MIT researchers tell WIRED.
Researchers use AI to design proteins that cut up other proteins
A protein is a chain of amino acids held together by what are called peptide bonds. On their own, those bonds are extremely stable; they're estimated to have a half-life of several hundred years. But in Earth's environment, most proteins don't last nearly that long. That's because organisms have evolved a handful of ways to catalyze the break-up of peptide bonds, which have diversified into countless specialized protein-digesting enzymes. Proteases are everywhere and generally make short work of
The maker of non-text AI model Jev valued at $7.5B just weeks after launch
What has users and large corporations so excited about Jev is TypeSafe’s claim that it works significantly faster and uses far fewer tokens than LLMs.