Skip to content
SPECIFICTION
Get listed

Fish Speech

github.com

From $11/mo Free plan WebLinuxAPISelf-hosted
Visit github.com
Spec score 8.4 #17 of 43 in AI voice cloning tools

Spec sheet

Purpose
Fish Speech is an open source multilingual text-to-speech system that generates expressive speech.Read 5 Oct 2026 · github.com
Integrations
The enterprise page lists support for real-time pipelines, WebRTC infrastructure, workflow automation, Vapi, Twilio, and Retell.Read 5 Oct 2026 · fish.audio
Support
Enterprise support includes 24/7 production support, a technical account manager, and a 99% uptime SLA.Read 5 Oct 2026 · fish.audio
License
The Fish Audio Research License permits research and non-commercial use free of charge, while commercial use requires a separate written license.Read 5 Oct 2026 · github.com
Commercial limits
The model license does not grant commercial rights, which require a separate written license from Fish Audio.Read 5 Oct 2026 · github.com
Emotion and prosody control
S2 supports fine-grained inline control of prosody and emotion through natural-language tags.Read 5 Oct 2026 · speech.fish.audio
Hardware requirement
The installation guide lists 24 GB of GPU memory for inference and Linux or WSL as system requirements.Read 5 Oct 2026 · speech.fish.audio
Languages
The repository describes S2 Pro as supporting more than 80 languages without phonemes or language-specific preprocessing.Read 5 Oct 2026 · github.com
Multiple speakers
S2 can use multi-speaker reference audio and speaker ID tokens to generate dialogue with multiple speakers in one generation.Read 5 Oct 2026 · speech.fish.audio
Security and compliance
Fish Audio says its SOC 2 Type II audit is underway and offers zero data retention, HIPAA-aligned configurations, and self-hosted deployments for enterprise workloads.Read 5 Oct 2026 · fish.audio
Streaming
The documentation describes SGLang serving optimizations including continuous batching, paged KV cache, CUDA graphs, and prefix caching.Read 5 Oct 2026 · speech.fish.audio
Voice cloning
S2 supports voice cloning from short reference samples, typically 10–30 seconds, without additional fine-tuning.Read 5 Oct 2026 · speech.fish.audio
Ways to run
The installation guide documents command-line, WebUI, server, and Docker setups, including CPU installation and GPU deployment.Read 5 Oct 2026 · speech.fish.audio

Plans and prices

Free Tier Free 8,000 credits monthly · up to 7 minutes generation · up to 500 characters per generation · 3 public voice slots · standard generation speed Read 5 Oct 2026 · fish.audio
Plus $11 a month $132 billed annually 250,000 credits monthly · up to 200 minutes · up to 15,000 characters per generation · priority generation · 1 professional voice slot Read 5 Oct 2026 · fish.audio
Pro $75 a month $900 billed annually 2,000,000 credits monthly · up to 1,620 minutes · 3 team seats · up to 30,000 characters per generation · 5 professional voice slots Read 5 Oct 2026 · fish.audio
Max $749 a month $8988 billed annually 25,000,000 credits monthly · up to 6,250 minutes · 10 team seats · 15 professional voice slots Read 5 Oct 2026 · fish.audio
Enterprise Priced on request volume pricing billed annually Pay as you go · zero data retention · on-premise deployment · SOC2 compliance · custom SSO coming soon Read 5 Oct 2026 · fish.audio

Every Fish Speech plan and price →

Where Specifiction places it

Alternatives to Fish SpeechAll alternatives →