Ship lifelike speech, voice cloning, and transcription with one API. Official Python and TypeScript SDKs. Sub-second latency. Pay-as-you-go pricing from your first call. S2.1 Pro running live. Pick a voice, type a line, hear it back. The same model behind HeyGen, Retell, and Sanas in production — no signup, no sales call, no demo environment. Trusted by teams building voice in production From signup to first audio in 5 minutes. No sales call required. Get an API key, install the SDK, and ship. What teams ship on Fish. Voice that holds up on camera Lip-syncable, emotion-aware TTS for AI avatar products. Inline direction tags drive performance, not just words. Real-time conversational AI Sub-second turn-taking over WebSocket. Streaming TTS and ASR in one stack. Interruption-aware. Dynamic spoken content. Notes-to-audio, prep tools, AI companions. Per-character pricing that scales with usage, not seats. Clone in 30 seconds. Or skip cloning entirely. IVC from 30 seconds of audio. PVC for studio-grade replicas. Or browse the voice library and ship without cloning. Built for the real-time stack. Open weights. Paid commercial license. Our open-source models — fish-speech, S1, and S2 — ship as open weights with a paid commercial license. Self-host in your VPC, on-prem, sovereign cloud, or air-gapped environment when production demands it. Self-host is an Enterprise-tier engagement — see below. 15,000+ direction tags. Inline in any call. [warm], [near-whisper], [reassuring] — direction travels with the text itself. No separate parameter, no list to pick from, no schema migration when the tag set grows. Audio Turing Test: 0.515. Listeners can't reliably distinguish S2.1 Pro from human in blind evaluation. 581 head-to-head comparisons. Methodology and raw audio published. $15 per million characters. From your first call.

Same model behind HeyGen, Pictoria, Dubbing AI, and Plaud. Pay-as-you-go from your first call. No "contact us" for production rates. Use our API. Or self-host the model Cloud API for any team building today. Self-host as a premium Enterprise engagement when production demands it. Hosted API · Any team Cloud API, pay-as-you-go, $15 per million characters. The fastest path to production for teams that don't need to operate the model themselves. WebSocket streaming, REST, Python + TypeScript SDKs $15 / 1M UTF-8 bytes — no commit Inline direction syntax in every call Same model that ships open-weight Self-host the model. Our open-source models — fish-speech, S1, S2 — ship as open weights with a paid commercial license. Deploy to your VPC, data center, sovereign cloud, or air-gapped environment. A premium engagement for high-volume teams needing data residency, fine-tuning, or regulated deployment. WebSocket streaming, REST, Python + TypeScript SDKs Effective floor: $120–150K/year Direct access to our research team Pricing that doesn't punish growth Pay-as-you-go from day one. No seat fees. No annual commits. No "contact us" for production rates. Frequently asked questions Coming from ElevenLabs, Cartesia, or Rime? Head-to-head breakdowns by capability, price, and contract terms. Same-shape API; most production migrations finish in under a week. The benchmarks, methodology, and raw audio Audio Turing Test results, blind-evaluation methodology, and the open-weights license. The proofs behind every claim on this page. Get to production this weekend Free credits to start. No card required. Same tier from prototype to scale.