AI4Bharat

by IIT Madras

IIT Madras Indic AI lab — IndicVoices + Kathbath + IndicSUPERB + IndicWav2Vec.

TL;DR

IIT Madras Indic AI lab — IndicVoices + Kathbath + IndicSUPERB + IndicWav2Vec.

Best for indic-language speech + NLP research, training data, and models. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Web, GitHub

What it is

AI4Bharat at IIT Madras built the canonical Indic speech stack: IndicVoices (16kh), Kathbath, Shrutilipi, IndicWav2Vec, IndicSUPERB. License: CC BY 4.0 across most releases.

Best for: Indic-language speech + NLP research, training data, and models.
Watch out for: Academic; models + corpora CC BY 4.0 (most).

Install / use

https://ai4bharat.iitm.ac.in/

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supported22
HIPAA eligibleNo

AI4Bharat vs Whipscribe

FeatureAI4BharatWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages2299
PlatformsWeb, GitHubWeb, API, MCP

Alternatives to AI4Bharat

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.