Fish Audio Launches S2.1 Pro Voice Model with $52M Seed Funding
Fish Audio officially released the production-ready voice cloning model S2.1 Pro and announced a $52 million seed funding round. The model focuses on real-time conversation and emotional expression, requiring only a few seconds of audio samples for high-fidelity voice cloning, directly challenging competitors in speed and cost.
Confirmed
- Funding & Launch: Fish Audio announced a $52M seed round and publicly launched S2.1 Pro. According to @davidyin44, the company has over 8 million cumulative users and $21 million in annual recurring revenue (ARR).
- Cloning Threshold: Multiple bloggers report the model clones voices from 5-15 seconds of audio, preserving tone, rhythm, emotion, and accent.
- Performance Metrics: Official first-syllable latency is 90ms, supporting real-time conversation; the model covers 83 languages and allows real-time emotion and style control via tags like [whispers sweetly], plus word-level control over pronunciation and pauses.
- Free Trial: @rohanpaulai adds the model is currently free for one month.
- Competitive Comparison: Fish Audio claims S2.1 Pro is 2x faster than Cartesia and costs 1/6 of ElevenLabs.
Why it matters
- Lowered Development Barrier: Second-level cloning and 90ms latency significantly reduce integration hurdles for real-time voice assistants, interactive game NPCs, etc.
- Intensified Market Competition: Direct comparisons with Cartesia and ElevenLabs on speed and cost signal an escalating price and performance war in TTS and voice cloning.
2026-07-29 ~ 2026-07-30 · 11 related posts
Primary sources
- Fish Audio says its new voice model clones a speaker from 5 seconds of audio — JafarNajafov · 2026-07-29
- Fish Audio says its S2.1 Pro voice model can start in 90 ms across 83 languages — testingcatalog · 2026-07-29
- Fish Audio says its voice clone now needs just 10 seconds of speech — aryanXmahajan · 2026-07-29
- Fish Audio Raises $52M Seed, Launches S2.1 Pro Voice Cloning Model — thisdudelikesAI · 2026-07-29
- [source] Fish Audio raises $52M seed for AI voice models as ARR hits $21M — davidyin44 · 2026-07-29
- Fish Audio marks one year with S2.1 Pro, its most advanced voice model yet — JafarNajafov · 2026-07-29
- [source] Fish Audio Makes S2.1 Pro Voice Model Free, Costs 1/6 of ElevenLabs — rohanpaul_ai · 2026-07-30
4 near-duplicate retellings: testingcatalog · LinusEkenstam · thisdudelikesAI · udmrzn