IndexTTS

by Bilibili

Bilibili's open-source TTS — Chinese + English bilingual.

TL;DR

Bilibili's open-source TTS — Chinese + English bilingual.

Best for chinese-market developers needing bilingual TTS with zero-shot cloning. Pricing: free (Apache-2.0 code, custom weight license).

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free (Apache-2.0 code, custom weight license)
Platforms
Linux

What it is

IndexTTS is Bilibili's open-source TTS model — strong Mandarin support with zero-shot voice cloning. Apache-2.0 code; weights under a separate license. Consent posture: open weights — operator-side enforcement.

Best for: Chinese-market developers needing bilingual TTS with zero-shot cloning.
Watch out for: Code is Apache-2.0 but weights have a separate license; mainly Chinese + English coverage.

Install / use

git clone https://github.com/index-tts/index-tts

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported2
HIPAA eligibleNo

IndexTTS vs Whipscribe

FeatureIndexTTSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree (Apache-2.0 code, custom weight license)free beta
Speaker diarization—Yes
Word timestamps—Yes
Streaming—No
Languages299
PlatformsLinuxWeb, API, MCP

Alternatives to IndexTTS

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.