MLC-LLM

by MLC AI

Compile + deploy LLMs (and Whisper) to phones / browsers / WebGPU.

TL;DR

Compile + deploy LLMs (and Whisper) to phones / browsers / WebGPU.

Best for cross-platform deployment of small Whisper models via TVM. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Linux, macOS, Windows, Android, iOS, Web

What it is

A universal LLM deployment framework via TVM Unity. Apache-2.0.

Best for: Cross-platform deployment of small Whisper models via TVM.
Watch out for: ASR support newer than text; quantization config heavy.

Install / use

pip install mlc-llm

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

MLC-LLM vs Whipscribe

FeatureMLC-LLMWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, Windows, Android, iOS, WebWeb, API, MCP

Alternatives to MLC-LLM

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.