What is Chatterbox Multilingual?

Chatterbox Multilingual is a text-to-speech model from Resemble AI. Chatterbox in 23 languages. On Leap it runs in one studio beside every other top model, with one account.

Which voices can I use?

23 voices, among them English, Arabic, Danish, German and Greek. You can hear each one in the studio before you run it.

How much text can it read in one run?

Up to 300 characters. You pay for the characters you send, with the price shown before you press go.

How is it different from Chatterbox?

Chatterbox Multilingual: Chatterbox in 23 languages. Chatterbox: Open-weight English speech with a dial for how expressive it is. They all run in the same studio, so you can try one prompt on each.

How much does a run cost?

A run costs $0.034. You see the exact price before you press go, and a run that fails costs nothing.

Is Chatterbox Multilingual free to try?

No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.034 (a run), so $5 covers 147 of those. You pay per run, in dollars, with no subscription.

Can I use what I make commercially?

Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.

Yes. Leap's REST API runs it as resemble-ai/chatterbox-multilingual, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.

Do I need a Resemble AI account?

No. Leap sends your request to Resemble AI's model and gives you what it makes. One Leap account runs Chatterbox Multilingual and every other model, in the studio, through the API and from your agents.

Chatterbox MultilingualAI text to speech

Chatterbox in 23 languages. On Leap, it sits beside 174 other models in one studio.

Text to speech

No subscription
Every top model, one account
Pay per run, priced before it starts

Listen / Nonna's rules, in Italian

0 / 9 s

Read the transcript

Nonna dice che la pasta va cotta al dente. Nonna dice anche che il telefono si usa solo per le emergenze. Nonna ha quattrocento follower.

AI text to speech

Chatterbox Multilingual at a glance

Chatterbox Multilingual is a text-to-speech model from Resemble AI. It makes speech from your text.

Made by: Resemble AI
Makes: Speech
Starts from: Your text
Voices: 23 to choose from
Text: Up to 300 characters
Price per run: $0.034
Updated: October 3, 2026

01Write the words, pick a voice
02See the exact price, then press go
03Keep it in your library, or take it further

Pick the right one

Chatterbox Multilingual and its siblings

Model	Best for	Price per run
Chatterbox Multilingual (this page)	Chatterbox in 23 languages.	$0.034
Chatterbox	Open-weight English speech with a dial for how expressive it is.	$0.034

Start with an idea

Three ways to try Chatterbox Multilingual

Side by side

More voice and sound models on Leap

Why Leap

Why creators make it on Leap

01
Every top model, side by side
175 models from Black Forest Labs, Google, ByteDance, Kuaishou, Alibaba and more, side by side in one studio.
See the models
02
One click, or full control
Character Studio, effects and recipes write the prompt for you. Or write your own for any model.
See the tools
03
Your work stays yours
Everything you make stays in your library while your account is active, and you own what you make here.
See what people make
04
One balance for everything
The studio, the API and your agents spend the same balance, and every run shows its price before it starts.
How pricing works

Questions

Chatterbox Multilingual, answered

What is Chatterbox Multilingual?: Chatterbox Multilingual is a text-to-speech model from Resemble AI. Chatterbox in 23 languages. On Leap it runs in one studio beside every other top model, with one account.
Which voices can I use?: 23 voices, among them English, Arabic, Danish, German and Greek. You can hear each one in the studio before you run it.
How much text can it read in one run?: Up to 300 characters. You pay for the characters you send, with the price shown before you press go.
How is it different from Chatterbox?: Chatterbox Multilingual: Chatterbox in 23 languages. Chatterbox: Open-weight English speech with a dial for how expressive it is. They all run in the same studio, so you can try one prompt on each.
How much does a run cost?: A run costs $0.034. You see the exact price before you press go, and a run that fails costs nothing.
Is Chatterbox Multilingual free to try?: No. There is no free credit: you add credit from $5, and your first top-up has no card fee. The cheapest run is $0.034 (a run), so $5 covers 147 of those. You pay per run, in dollars, with no subscription.
Can I use what I make commercially?: Yes. You own what you make on Leap, so you can use it commercially, and we never train AI on it. The people and brands shown in a result can still have rights in it; the Terms say more.
Is there an API?: Yes. Leap's REST API runs it as resemble-ai/chatterbox-multilingual, at the same price per run as the studio, and agents can call it through Leap's MCP server. The request is at the bottom of this page.
Do I need a Resemble AI account?: No. Leap sends your request to Resemble AI's model and gives you what it makes. One Leap account runs Chatterbox Multilingual and every other model, in the studio, through the API and from your agents.

Your idea, Chatterbox Multilingual.

Every run shows its price before it starts, and one that fails costs nothing.

Make it with Chatterbox Multilingual

For developers

Run Chatterbox Multilingual from code

API docs

Model ID: resemble-ai/chatterbox-multilingual
Makes: Voice and sound
Pricing: Per run, quoted first: POST /v1/quotes

Inputs

What the model takes. Leave out anything with a default.

Texttext

Text, up to 300 characters, required

Voicevoice

English, Arabic, Danish, German, Greek, Spanish, Finnish, French, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese, Russian, Swedish, Swahili, Turkish, Chinese. Default: English

Custom Audio Languagesettings.custom_audio_language

Exaggerationsettings.exaggeration

0.25 to 2. Default: 0.5Controls speech expressiveness and emotional intensity (0.25-2.0).

Temperaturesettings.temperature

0.05 to 2. Default: 0.8Controls randomness and variation in generation (0.05-2.0).

CFG Scalesettings.cfg_scale

0 to 1. Default: 0.5Configuration/pace weight controlling generation guidance (0.0-1.0).

Seedseed

0 to 4294967295The same seed and input give the same image.

The request

The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result when the run finishes within a minute; a longer one is read again by its ID. Agents can call it through the MCP server at app.tryleap.ai/api/mcp.

curl https://api.tryleap.ai/v1/generations \  -H "x-api-key: $LEAP_API_KEY" \  -H "content-type: application/json" \  -H "prefer: wait=60" \  -d '{    "model": "resemble-ai/chatterbox-multilingual",    "input": {      "text": "Nonna dice che la pasta va cotta al dente. Nonna dice anche che il telefono si usa solo per le emergenze. Nonna ha quattrocento follower."    }  }' # Video often outlasts the wait and answers "queued" or "running".# Put its "id" in GENERATION_ID and read it again until it is done:# curl https://api.tryleap.ai/v1/generations/$GENERATION_ID -H "x-api-key: $LEAP_API_KEY"