Try PixVerse C1 Reference-to-Video Model from PixVerse →
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Voice Clone models

Voice cloning models and APIs.

Clone a voice from a short reference recording and use it to speak new text, in one language or many.

Showing 9 of 9 models
MOSS-TTS-v1.5 - AI model cover image

MOSS-TTS-v1.5

OpenMOSS

OpenMOSS MOSS-TTS v1.5 turns text into natural speech, with optional zero-shot voice cloning from a reference clip. It supports 31 languages plus pause and pronunciation control.

Voice Clonetext-to-speechtransformers
Run
OmniVoice - AI model cover image

OmniVoice

k2-fsa

OmniVoice by k2-fsa generates 24 kHz speech from text in 600+ languages. Clone a speaker from a short reference clip or design a new voice from attributes.

Voice Clonetext-to-speechtransformers
Run
tada-3b-ml - AI model cover image

tada-3b-ml

humeai

TADA is a unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. By leveraging a novel tokenizer and architectural design, TADA achieves high-fidelity synthesis and generation with a fraction of the computational overhead required by traditional models.

Voice Clonetext-to-speechtransformers
Run
s2-pro - AI model cover image

s2-pro

fishaudio

Generates high-quality speech from text using advanced TTS technology with support for voice cloning and multi-speaker synthesis.

Voice Clonetext-to-speechtransformers
Run
kani-tts-2-en - AI model cover image

kani-tts-2-en

nineninesix

Generates natural-sounding speech from text with support for multi-speaker voice cloning and fast inference capabilities.

Voice Clonetext-to-speechtransformers
Run
chatterbox-turbo - AI model cover image

chatterbox-turbo

resemble-ai

The fastest open source TTS model without sacrificing quality.

Voice Clonespeech-to-textspeech-to-speech
Run
chatterbox-multilingual - AI model cover image

chatterbox-multilingual

resemble-ai

Generate expressive, natural speech in 23 languages. Features instant voice cloning from short audio, emotion control, and seamless cross-language voice transfer.

Voice Clonespeech-to-textspeech-to-speech
Run
RVC-Voice-Clone-Youtube - AI model cover image

RVC-Voice-Clone-Youtube

wiro

Clone any voice and cover any YouTube song with it. This tool lets you apply a custom-trained RVC voice model to recreate any YouTube song in that voice.

Voice Clonevoice clonerealistic voice
Run
voice-clone - AI model cover image

voice-clone

wiro

A text-to-speech tool by Coqui that generates natural-sounding speech from text and performs voice cloning by taking a 6-second voice sample to produce new voice outputs.

Voice Clone
Run

How to pick a voice cloning model

Voice cloning models learn a voice from a short recording and use it to read new text. Check the languages each one supports and how much reference audio it needs.

Many languages

OmniVoice clones a speaker from a short clip in more than 600 languages, and can also design a new voice from a description. MOSS-TTS v1.5 supports 31 languages, with control over pauses and pronunciation.

Clone from a short sample

Voice Clone needs about 6 seconds of audio before it can speak new text in that voice.

Songs

RVC Voice Clone applies a trained voice model to a song from a YouTube link, for covers.

Frequently asked questions

How much audio do I need?

Most models here work from a clip of a few seconds, and Voice Clone asks for about 6. A clean recording without music or background noise matters more than length.

Can the cloned voice speak another language?

Yes, with the multilingual models. Chatterbox Multilingual is built to carry a voice across languages, and OmniVoice and MOSS-TTS v1.5 cover dozens to hundreds of them.

Whose voice can I clone?

Only voices you have the rights to use, such as your own or a speaker who agreed to it.