# Fish Audio: what I've logged

> Fish Audio comes up in 2 posts of my AI log, from March 2026 to October 2026, and each item below links to the primary source. The releases I logged include Fish Audio Drama 3 and Fish Audio S2 Pro, filed under open weights, agents and coding and image, video, world.

## Items

1. **Fish Audio Drama 3** (Fish Audio, 14 Oct 2026): A 35B text-to-speech model with 3B active parameters that carries up to 16 speakers in one text, with voice cloning and tags for sounds like sighs and laughs. [Primary source](https://huggingface.co/fishaudio/drama-3) · [Post](https://heyaliasif.com/ai/2026-10-15-jais-3-step-5-ling-drama-3#item-4)
2. **Fish Audio S2 Pro** (Fish Audio, 9 Mar 2026): An open text-to-speech model with fine-grained control over delivery. [Primary source](https://huggingface.co/fishaudio/s2-pro) · [Post](https://heyaliasif.com/ai/2026-03-09-week-in-ai#item-4)

## Posts

- 2026-10-15 [Jais 3 goes open, Step 5 and Ling 3.1 land, Drama 3 speaks](https://heyaliasif.com/ai/2026-10-15-jais-3-step-5-ling-drama-3)
- 2026-03-09 [Nemotron 3 Super opens up and Gemini Embedding 2 goes multimodal](https://heyaliasif.com/ai/2026-03-09-week-in-ai)

Canonical: https://heyaliasif.com/ai/topics/fish-audio