Fish Audio

Audio & Music Gen · Free + paid

Expressive multilingual speech models and voice APIs, open and hosted

At a glance

Made by
Hanabi AI Inc.
Korean
UI in Korean
API
Yes
Available on
Web, API
Open source
FISH AUDIO COMMUNITY LICENSE (S2-Pro weights are under the Fish Audio Research License)
GitHub
33,076 stars · NOASSERTION

What is Fish Audio?

Fish Audio is a voice AI platform whose core features can all be used in three ways: a web app (no code), a REST API, and official SDKs. It turns text into realistic speech, clones voices from a 15-second clip, and also offers speech recognition with multiple speakers and emotion markers. Emotion tags such as [angry] and [whispering] control expression, and any voice can speak more than 30 languages. It also has a library of over 2 million user-uploaded voices, avatar lip sync, and image and video generation models.

  • Text-to-speech (control expression with emotion and special tags)
  • Voice cloning from a 15-second clip, professional voice cloning
  • Speech recognition with multiple speakers and emotion markers (Speech to Text)
  • Real-time streaming and end-to-end voice agents
  • Supports 30+ languages
  • Library of 2 million+ voices
  • Voice Design, voice changer, Story Studio, music and sound effect generation
  • Avatar lip sync and image and video generation models

Who uses Fish Audio and for what

  • Voiceovers for YouTube, ads, and explainer videos
  • Audiobook narration to ACX/Audible specifications
  • Game and animation character voices and customer support chatbot voices

Pricing

What you get for free — Yes (8,000 credits/month, up to 7 minutes of generation, 500 characters per generation, 3 public voice slots)

PlanPriceMain limits
Free tier$0/mo8,000 credits/month, up to 7 minutes, 500 characters per generation
Plus (billed annually)$11250,000 credits/month, up to 200 minutes, 15,000 characters per generation, 1 professional voice slot
Plus (billed monthly)$15/mo250,000 credits/month
Pro (billed annually)$752,000,000 credits/month, up to 1,620 minutes, 3 team seats, 5 professional voice slots
Pro (billed monthly)$100/mo2,000,000 credits per month
Max (billed annually)$74925,000,000 credits/month, up to 6,250 minutes, 10 team seats, 15 professional voice slots
Max (billed monthly)$999/mo25,000,000 credits/month
EnterpriseContact salesCustom, billed annually based on usage, on-premises, SOC2

Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying. · Official pricing page

AI tools similar to Fish Audio (alternatives)

Fish Audio vs. alternatives at a glance

AIPricingCombos on the mapConnected toolsFreeCheapest monthlyKorean
Fish AudioFree + paid05Yes$11/moYes
ElevenLabsFree + paid495Yes$6/moYes
TypecastFree + paid05Yes$15/moYes
Coqui TTSFree05———
OpenAI TTSFree + paid185———

3 of these 5 tools have a free plan. Cheapest paid plan: ElevenLabs ($6/mo).

Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.

Fish Audio on AI Galaxy Map

  • One of 15 AI tools in the Audio & Music Gen field.
  • Connected to 5 other tools — #1 in its field.

Frequently asked questions

Can I use Fish Audio for free?

Yes (8,000 credits/month, up to 7 minutes of generation, 500 characters per generation, 3 public voice slots). Prices can change, so check the official site before paying.

What AI can I use instead of Fish Audio?

Tools that do the same job, such as ElevenLabs, Typecast, Coqui TTS, OpenAI TTS, are connected to it on the map.

Can I use Fish Audio in Korean?

UI in Korean

Sources (official pages)

Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.

HomeTrendsTools