Fish Speech

Web · Linux · Self-hosted · API · paid plans from $11/mo

Freedom report

Two barsScore 6.4

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely2 of 6 device platforms
DocumentedPlans, terms and facts published

Fish Speech is ranked #7 of 41 in game voice generators on Freedom251. It runs on API, Linux, Self-hosted, Web. There is a free plan. Paid plans start at $11/mo.

Fish Speech plans and pricing

All plans

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 fish.audio · 5 Oct 2026

Plus $11/mo $132 billed annually 250,000 credits monthly · up to 200 minutes · up to 15,000 characters per generation · priority generation · 1 professional voice slot fish.audio · 5 Oct 2026

Pro $75/mo $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 fish.audio · 5 Oct 2026

Max $749/mo $8988 billed annually 25,000,000 credits monthly · up to 6,250 minutes · 10 team seats · 15 professional voice slots fish.audio · 5 Oct 2026

Enterprise Not published volume pricing billed annually Pay as you go · zero data retention · on-premise deployment · SOC2 compliance · custom SSO coming soon fish.audio · 5 Oct 2026

Compared on game voice generators

Commercial use: No
API access: Yes

Best Fish Speech alternatives

See all 20

Two bars Kokoro TTS Free tier No. 1Free6.6 Two bars Speechify Free tier No. 2$29/mo6.6 Two bars Altered Studio Free tier No. 3$30/mo6.5 Two bars Voice Creator Pro Free tier No. 4$5/mo6.5 One bar AnnoMotion Free tier No. 5£4.50/mo6.4 One bar Cartesia Sonic Free tier No. 6$5/mo6.4

The record

Purpose: Fish Speech is an open source multilingual text-to-speech system that generates expressive speech.
Emotion and prosody control: S2 supports fine-grained inline control of prosody and emotion through natural-language tags.
Languages: The repository describes S2 Pro as supporting more than 80 languages without phonemes or language-specific preprocessing.
Voice cloning: S2 supports voice cloning from short reference samples, typically 10–30 seconds, without additional fine-tuning.
Multiple speakers: S2 can use multi-speaker reference audio and speaker ID tokens to generate dialogue with multiple speakers in one generation.
Streaming: The documentation describes SGLang serving optimizations including continuous batching, paged KV cache, CUDA graphs, and prefix caching.
Ways to run: The installation guide documents command-line, WebUI, server, and Docker setups, including CPU installation and GPU deployment.
Hardware requirement: The installation guide lists 24 GB of GPU memory for inference and Linux or WSL as system requirements.
License: The Fish Audio Research License permits research and non-commercial use free of charge, while commercial use requires a separate written license.
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.
Integrations: The enterprise page lists support for real-time pipelines, WebRTC infrastructure, workflow automation, Vapi, Twilio, and Retell.
Support: Enterprise support includes 24/7 production support, a technical account manager, and a 99% uptime SLA.
Commercial limits: The model license does not grant commercial rights, which require a separate written license from Fish Audio.
Price from: $11/mo

Where it ranks on Freedom251

Best Game Voice Generators in 2026#7 of 41
Best Voice Cloning Software in 2026#4 of 24

Is Fish Speech yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote Fish Speech

Sources

github.com/fishaudio/fish-speech· checked 5 Oct 2026
speech.fish.audio· checked 5 Oct 2026
speech.fish.audio/install/· checked 5 Oct 2026
github.com/fishaudio/fish-speech/blob/main/LICENSE· checked 5 Oct 2026
fish.audio/enterprise/· checked 5 Oct 2026
fish.audio/plan/· checked 5 Oct 2026