Fishaudio
Try Drama mode

Expressive Fish Audio voices you can direct line by line

Short clips are easy; long takes are the real test. Fish Audio keeps tone, breath and feeling steady from opening line to closing line.

Abstract impressionist oil painting with soft lavender, cream, peach and dusty blue brushstrokes filling a wide landscape canvas, used as a calm backdrop
Write your own line

I'm okay. Honestly. <whisper>Keep going without me.</whisper>

Emotions

[angry][sad][embarrassed][emphasis][whispering][soft][breathy][excited]

Special

[laughing][chuckling][sighing][sobbing][clear throat][pause][long pause]
Generate & play
Running on the Fish Audio expressive engine
Create yours

Building alongside
global innovators

See their stories
HeyGen logo Retell AI logo OpenArt markOpenArt wordmark Sanas logo LiveKit logo Telnyx logo Novita AI logo Viggle markViggle wordmark Comfy logo Runware logo
ACE Studio markACE Studio wordmark Clout Kitchen logo Innertune markInnertune wordmark VoiceDrop markVoiceDrop wordmark Final Round markFinal Round wordmark Emochi markEmochi wordmark Pictoria markPictoria wordmark
Blessed logo BookTok logo Arno logo Other Half logo Sekai logo Bimo logo VoiceRun markVoiceRun lettersVoiceRun suffix

Meet the newest Fish Audio model
A voice engine that never sounds synthetic

Fish Audio customer support voice card: soft pastel abstract painting in blush pink, mint and grey brushstrokes

Customer support

Patient · Calm · Clear

Narrator voice card: dreamy abstract painting in lilac, cream and pale violet strokes

Narrator

Immersive · Layered · Warm

Character voice card: expressive abstract painting with dusty rose, slate blue and ivory brushwork

Character

Bold · Theatrical · Vivid

Hear it live

Studio-grade AI voices for video, audiobooks and characters

Get started

Voice-AI APIs built for enterprise teams

Live streaming, instant cloning and transcription in one stack. Fish Audio supplies the parts you need to ship production voice agents.

Light UI illustration of a text to speech panel with a greeting script, guide lines and floating speaker bubbles

Text to Speech

Very low latency, top marks for control and expression

Soft UI illustration of speech to text with emotion labels like Happy and speaker tags beside a flowing waveform

Speech to Text

Transcripts with speaker labels, emotion tags and plain-language notes

Pale UI illustration of a voice agent card with a named voice preview and a playback bar

Voice Agents

A full pipeline for conversational agents

Minimal UI illustration of voice cloning with a fingerprint motif over thin grid lines

Clone Any Voice

High-fidelity copies from a 15-second sample

Soft UI illustration of greeting chips in many languages, including Hindi, Thai, Chinese, Spanish, Russian and Korean

Multilingual Support

One voice, more than 30 languages

Loved by 8M+ creators, ready when you are

Animated film still of a fluffy blue creature sitting on railway tracks beside a rusty red truck as a freight train approaches, bold cartoon title above
Round channel avatar with a cute cartoon monster face Tiny Beast Tales

Animated shorts built with Image & Video

YouTube thumbnail of a middle-aged presenter in a home studio talking about AI character voices, bright bold text overlay
Small round headshot of a smiling bearded man Marcus Hale

Characters revived through Voice Cloning

Tech tutorial thumbnail with a young man at a desk with charts and a laptop, clean modern graphics
Small round headshot of a young man wearing glasses Priya | Code

Video narration made with Text to Speech

Audiobook channel thumbnail showing an open book with warm lamp light and a storyteller in a cozy room
Small round headshot of a friendly man with short hair Odd Road Stories

Full books produced with Audiobooks

Futuristic thumbnail of a white humanoid robot beside a vintage studio microphone on a deep blue background
Small round avatar of a stylised robot head Neon Byte AI

2M+ voices to browse in the Voice Library

Join them

Teams that demand more from their voice stack

The multilingual output stunned us. Arabic, French and Japanese voiceovers all came back with native-sounding delivery.

Round avatar of a young man with dark hair in a casual shirt

@lenaontape

YouTube

We ran Fish Audio head to head with a big-name rival, and it won on authenticity and emotional range. It is now our default.

Round illustrated avatar of a character with a confident expression

Orbit Studio

X

Moving away from booked voice actors cut our turnaround in half and gave us visibly better quality on every episode.

Round avatar of a smiling woman with shoulder-length hair

Kestrel Media

YouTube

Of every generator we tested, the natural cadence here sat in a class of its own.

Round bright yellow badge avatar with bold black hand-lettered tech text

ByteDesk Tech

YouTube

Our bedtime-story channel finally sounds warm and human, and listeners stay to the very end.

Round portrait avatar of a woman with curly auburn hair smiling in soft daylight

Juniper Reads

TikTok

Our NPCs gained real emotional range without a single recording session.

Round avatar showing a minimal teal game studio emblem on a dark background

Halcyon Games

X

I cloned my own voice for ad reads and nobody noticed the switch.

Round headshot of a woman podcaster with headphones around her neck in a warm studio

Mara Quinn

Podcast

Latency is low enough that our phone agent feels like a live person.

Round avatar with an abstract blue signal-wave logo on white

Signal Lab

LinkedIn

2,000,000+ Voices

Endless range from community-made voices

The Fish Audio library holds more than two million voices, suited to storytelling, punchy ads, immersive audiobooks and much more.

Collage of circular portrait photos of diverse young voice creators, warm studio lighting, overlapping bubbles on a beige panel

30+ AI Models

Make anything with top image, video and avatar models

Veo, Kling, Seedance, GPT Image, Creatify and others, always current and ready to go. Short on ideas? Browse community pieces and remix them.

AI-generated portrait of a young woman with wavy brown hair holding a small skincare bottle in a bedroom, selfie framing
AI-generated cinematic scene of a figure walking under a dusky violet sky, wide framing
AI-generated portrait of a smiling man with curly black hair in a brown leather jacket and checked shirt, indoor home setting
AI-generated product shot of a glossy drink can on a pastel set with soft studio light
AI-generated close-up of a young woman with freckles in golden-hour light, shallow depth of field
AI-generated vertical video frame of a stylish creator speaking to camera in a softly lit city apartment

Recent news

Three people from a voice AI team seated at a home kitchen table, warm interior, with a large white headline across the frame

Drama mode: our most emotive speech model to date

Celebration banner with a sound-bar logo on a vivid purple-to-red gradient scattered with colourful confetti

Five models, a small team and one busy year

Fish Audio engineering article banner with large dark headline on a soft lavender and pink gradient

How we rebuilt inference to make S2.1 Pro faster and leaner

Give every script a voice that feels alive

Start now

Common questions

Which languages does Fish Audio support for speech?

English, Spanish, French, German, Arabic, Chinese, Japanese and Korean today, with more on the way.

How does voice cloning work for creators?

A short recording is analysed for pitch, tone and rhythm to build a model. Fish Audio needs roughly ten seconds of clean audio.

Which AI voice suits YouTube videos?

Expressive narrators in many languages, ready for tutorials, explainers and documentaries without a mic or hired talent.

Can I change emotion inside one sentence?

Yes. Wrap words in tags such as [soft] or a whisper tag and only those words shift.

What makes a synthetic voice sound human?

Natural pauses, breath, emphasis and steady emotion across long takes, all of which tags let you shape.

What voice works best for audiobooks?

Pick a warm narrator with even pacing, then use chapter tags to lift dialogue and slow key moments.

Can I voice game characters?

Design or clone a persona, then push it toward anger, laughter or a hush line by line.

Get started
Get started