Voice Cloning - Fish Audio

Build a reusable voice model from your own audio, then use it anywhere you generate speech. You get back a voice id — pass it as reference_id to Text to Speech and every generation speaks in that voice. Works from the API directly, the Python library, or JavaScript.

Use it in the web app

No code — clone a voice in the browser.

API reference

Every field for POST /model.

Cookbooks

Instant clones, training, and reuse.

When to use it

Brand voice

One consistent voice across product, ads, and IVR.

Personal voice

Clone your own voice for narration or assistants.

Characters

Distinct voices for games, stories, and dialogue.

Dubbing & localization

Keep a speaker’s identity across languages.

Quick start

Send one or more audio samples, get back a voice model. Choose your implementation:

from fishaudio import FishAudio

client = FishAudio()  # reads FISH_API_KEY

with open("sample.wav", "rb") as f:
    voice = client.voices.create(
        title="My Voice",
        voices=[f.read()],
        description="Cloned from a studio sample",
        visibility="private",
    )

print(voice.id, voice.state)

curl --request POST https://api.fish.audio/model \
  --header "Authorization: Bearer $FISH_API_KEY" \
  --form type=tts \
  --form title="My Voice" \
  --form "description=Cloned from a studio sample" \
  --form visibility=private \
  --form train_mode=fast \
  --form voices=@sample.wav

# Returns the new model, including its "_id" and "state".

import { FishAudioClient } from "fish-audio";
import { readFile } from "fs/promises";

const client = new FishAudioClient({ apiKey: process.env.FISH_API_KEY });

const sample = await readFile("reference.wav");

const voice = await client.voices.ivc.create({
  title: "My Voice",
  voices: [new File([sample], "reference.wav")],
  description: "Cloned from a studio sample",
  visibility: "private",
});

console.log(voice._id, voice.state);

Use your cloned voice

Pass the voice id as reference_id to Text to Speech — exactly like any other voice.

audio = client.tts.convert(
    text="Now I speak in my cloned voice.",
    reference_id=voice.id,
)

curl --request POST https://api.fish.audio/v1/tts \
  --header "Authorization: Bearer $FISH_API_KEY" \
  --header "Content-Type: application/json" \
  --header "model: s2-pro" \
  --data '{ "text": "Now I speak in my cloned voice.", "reference_id": "YOUR_VOICE_ID" }' \
  --output out.mp3

Implementation details

Sample quality

Clean, mono, single-speaker audio gives the best result. A short clip works for a quick clone; a minute or two of clear speech improves fidelity. Avoid background music, reverb, and overlapping voices.

Multiple samples

Pass several clips to capture more range. You can also supply the matching transcripts as texts to sharpen pronunciation.

voice = client.voices.create(
    title="My Voice",
    voices=[open("a.wav", "rb").read(), open("b.wav", "rb").read()],
    texts=["Transcript of clip A.", "Transcript of clip B."],
)

curl --request POST https://api.fish.audio/model \
  --header "Authorization: Bearer $FISH_API_KEY" \
  --form type=tts \
  --form title="My Voice" \
  --form voices=@a.wav \
  --form voices=@b.wav

Visibility

Models are private by default. Set unlist for a shareable link, or public to publish to the Voice Library. You can change this later — see Manage Voices.

Instant vs. persistent clones

There are two ways to clone:

Persistent model (above) — train once with voices.create(), get back a reusable id. Best when you’ll use the same voice repeatedly.
Instant clone — pass reference audio inline on each generation with no model to manage. Best for one-off or per-request voices.

For an instant clone, send the reference audio (and its transcript) directly to Text to Speech via references instead of reference_id:

Python

from fishaudio import FishAudio
from fishaudio.types import ReferenceAudio

client = FishAudio()

with open("reference.wav", "rb") as f:
    audio = client.tts.convert(
        text="This will sound like the reference voice.",
        references=[ReferenceAudio(
            audio=f.read(),
            text="The exact words spoken in the reference clip.",
        )],
    )

Pass several ReferenceAudio entries to capture more range, just as you would with multiple samples in a persistent model. The matching text for each clip sharpens pronunciation.

Sample audio requirements

Samples can be .wav, .mp3, .m4a, or .opus. Aim for at least 10 seconds per clip; a minute or two of clear, single-speaker speech improves fidelity. enhance_audio_quality (on by default) removes background noise and normalizes levels before training:

Python

voice = client.voices.create(
    title="My Voice",
    voices=[open("sample.wav", "rb").read()],
    enhance_audio_quality=True,
)

Leave it on for noisy or lower-quality recordings. If your audio is already clean and studio-grade, turning it off (enhance_audio_quality=False) avoids any extra processing.

Model state

A new model reports a state field that moves from created to trained (or failed). With train_mode="fast" (the default) the voice is usable almost immediately, so most clones return already trained.

Python

voice = client.voices.create(title="My Voice", voices=[sample])
print(voice.state)  # "trained"

If a generation rejects the reference_id, re-fetch the model and confirm its state before using it in Text to Speech:

Python

voice = client.voices.get(voice.id)
if voice.state == "trained":
    audio = client.tts.convert(text="Hello.", reference_id=voice.id)

Going further

Speak with your voice

Use reference_id in any generation.

Manage your voices

List, update, and delete your voice models.

Cloning best practices

Get the most natural results from your samples.

Create Model API

Every field for POST /model.

Use it in the web app

API reference

Cookbooks

​When to use it

Brand voice

Personal voice

Characters

Dubbing & localization

​Quick start

​Use your cloned voice

​Implementation details

​Sample quality

​Multiple samples

​Visibility

​Instant vs. persistent clones

​Sample audio requirements

​Model state

​Going further

Speak with your voice

Manage your voices

Cloning best practices

Create Model API

When to use it

Quick start

Use your cloned voice

Implementation details

Sample quality

Multiple samples

Visibility

Instant vs. persistent clones

Sample audio requirements

Model state

Going further