Index TTS

Index TTS AI Audio Generator is a powerful tool for turning text into natural, expressive speech with clear pronunciation, realistic voices, and flexible audio generation.

Documentation

IndexTTS2 Online Voice Cloning & Text to Speech

Clone a voice from a short reference and generate English or Chinese speech with IndexTTS2 in the browser. Need Japanese, Spanish, Arabic or pace control? Switch to IndexTTS 2.5 in the same generator.

Model

Choose the IndexTTS model for this generation.

Reference voice

Add 3–30 seconds of clear, single-speaker audio.

0 / —

Supports English and Chinese text.Punctuation helps control pauses and delivery.

Output

Waiting

Generated audio will appear here.

Add a reference voice and text to get started.

WAV output · Signed-in generations can be viewed in History.

By generating, you confirm that you are 18 or older and that you own this reference voice or have permission to use it. Use is subject to our Terms and Acceptable Use Policy.

IndexTTS models

Choose the model that fits this generation

Both models use the same voice library, History, account, and pricing. Choose based on language and controls.

Available online

IndexTTS2

English & Chinese · emotion

Explore IndexTTS2

Latest · Available online

IndexTTS 2.5

Five languages · emotion · pace

Explore IndexTTS 2.5

IndexTTS model samples

Compare official IndexTTS samples

Use official source samples to compare IndexTTS2 with the latest multilingual IndexTTS 2.5 model before choosing a model for generation.

Choose a sample

How it works

One voice workflow across IndexTTS models

Use the same reference-voice flow, then choose the model and controls that fit the language and delivery you need.

01

Add a reference voice

Upload a WAV or MP3 file, or record 3–30 seconds of clear, single-speaker speech. Signed-in users can save useful references to My Voices.

02

Enter text and choose controls

Choose an available IndexTTS model. IndexTTS 2.5 adds explicit language and pace controls; IndexTTS2 keeps the established English and Chinese flow.

03

Generate, listen and download

Generate speech, listen to the result, retry when needed, and download WAV output. Signed-in generations are kept in History within the plan retention period.

Why IndexTTS Online

Built for repeat voice generation

Use the IndexTTS models without setting up a local GPU, then keep useful reference voices and generated audio available for later work.

No local setup

Use IndexTTS in the browser

Upload or record a reference and generate speech without installing the model or maintaining a GPU environment.

Saved Voices

Reuse reference voices

Save useful reference voices to your account so you do not need to find and upload the same file every session.

History & WAV

Return to generated audio

Authenticated history keeps recent results available for playback and download within your plan retention period.

Pricing

Choose the plan that fits how you create.

Prepare your first task for free, sign in to use the finite Free trial, get 10 minutes for a one-off project, or choose Pro: 100 minutes/month at $14.99, or 180 minutes/month billed yearly at $149.99.

Free Trial

For trying the real workflow after sign-in

$0

Finite signed-in trial. No daily reset.

  • 2 successful IndexTTS2 generations total
  • 1 successful IndexTTS 2.5 Premium trial
  • Up to 60 characters per generation
  • 5 Saved Voices · 30-day History
  • No credit card required

Start free trial

ONE-TIME

Voice Pack

One payment for a real project

$4.99one-time

A simple upgrade when the Free trial is not enough.

  • 10 minutes of generated audio
  • Full access to IndexTTS2 + IndexTTS 2.5
  • Emotion & pace controls
  • Use anytime within 30 days
  • Standard paid processing
  • No subscription or auto-renew

BEST VALUE

Pro

For regular voice production

$14.99 /month

About 3.3× more audio minutes per dollar than a Voice Pack.

  • 100 generated-audio minutes every month
  • Up to 1,000 characters per generation
  • Keep up to 30 reusable Saved Voices
  • Full IndexTTS 2.5: 5 languages, emotion and pace controls
  • Priority processing during busy periods
  • IndexTTS2 API included · 100 min shared with the website
  • 180-day generation history

Compare all plan details →

Start here

Popular guides for better voice cloning

Start with the workflows that most directly improve inputs, model choice, and output diagnosis.

[

7 min read

How to Clone a Voice with IndexTTS Online: A Practical Start-to-Finish Guide

A practical workflow for preparing reference audio, generating speech, checking quality, and avoiding common voice-cloning mistakes.

Read guide

](https://indextts.online/blog/how-to-clone-a-voice-with-indextts-online)[

6 min read

IndexTTS2 vs IndexTTS 2.5: Which Model Should You Use?

A practical comparison of IndexTTS2 and IndexTTS 2.5 based on language coverage, controls, workflow needs, and production trade-offs.

Read guide

](https://indextts.online/blog/indextts2-vs-indextts-2-5)[

6 min read

Multilingual Voice Cloning: A Production Workflow for English, Chinese, Japanese, Spanish, and Arabic

A practical multilingual voice-cloning workflow covering script preparation, pronunciation checks, brand terms, review, and consistency across languages.

Read guide

](https://indextts.online/blog/multilingual-voice-cloning-workflow)[

6 min read

Voice Cloning Troubleshooting: Why Generated Speech Sounds Wrong and What to Fix First

Diagnose common voice-cloning problems by separating reference-audio issues, script issues, pronunciation, model choice, pacing, and output review.

Read guide

](https://indextts.online/blog/voice-cloning-troubleshooting)

Browse all guides

FAQ

Questions before you generate

Practical answers about IndexTTS Online, available models, usage limits, and reference audio.

Generate online

Turn a reference voice into speech

Add a short reference, enter your text, and generate with the IndexTTS model that fits the job.

Generate speech