About Fish Audio
Fish Audio is a text-to-speech and voice cloning service with a large library of voices and emotion controls. It is used for voiceovers, audiobooks, character voices and conversational agents.
What it does
You type text, add tags such as laughing, whispering or sighing, and generate speech with the voice you pick. The service supports voice cloning from a short sample, speech-to-text, and avatar lip-sync that matches a voice to an image or video. A developer API lets teams add the same voices to their own apps.
Key features
- Text to speech with emotion tags
- Voice cloning from short samples
- Speech to text
- Avatar lip-sync for images and videos
- API access for developers
Who it's for
Video producers, audiobook narrators, game and animation teams, and developers building voice assistants. Creators who want expressive character voices without a studio will find it useful.
Pricing and good to know
You can sign up for free, and paid plans add more usage, voices and API access. Check the pricing page for current rates. Only clone voices from recordings you have permission to use, and follow the site's terms on that point.
Highlights
- Generate speech with emotion tags
- Clone a voice from a short sample
- Convert speech to text
- Lip-sync an avatar to a voice
- Add voices to apps through the API
