New ModelsOpen weights
Drama 3
Fish Audio releases Drama 3, open-weights TTS you can direct
Drama 3 is Fish Audio's open-weights text-to-speech model that lets you direct how a voice sounds. It was Wolfram's pick of the week.
Fish Audio AI Releases: Drama 3, Fish Audio STT & Fish Audio S2
ThursdAI — the weekly AI news podcast hosted by Alex Volkov — has covered 3 Fish Audio releases since Mar 2026, most recently Drama 3 on Oct 15, 2026. Highlights include Fish Audio S2, Drama 3, Fish Audio STT. 2 of them shipped with open weights. Every entry below has primary-source links and the episode segment where we covered it live, plus key numbers where we have them.
3 releases2 open weights4 episodesMar 2026 – Oct 2026
April 2026 1
Products & Apps
Fish Audio STT
Fish Audio launches speech-to-text with automatic emotion tagging
Fish Audio released a speech-to-text product with automatic emotion tagging that feeds directly into its S2 TTS pipeline. The panel saw it as another sign that voice tooling is rapidly commoditizing and challenging incumbent speech providers.
March 2026 1
New ModelsOpen weights
Fish Audio S2
Fish Audio S2 open TTS hits sub-150ms latency
Fish Audio S2 is a fully open-source TTS model with inline emotion control via free-text bracket tags like gasp, laughter, and long pause. Alex demoed it live with an OpenClaw skill that let his 5-year-old talk to a voice clone of 'Rocky' from Project Hail Mary; Wolfram called it 'ElevenLabs V3 for free.'
<150ms Fish Audio S2 TTS latency
Get this every week
Never miss a Fish Audio launch — we cover every release live, every Thursday.