llm.c

by Andrej Karpathy

Andrej Karpathy's bare-metal C training code — reference for compact ASR.

Looking at llm.c? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for studying minimal training loops adaptable to small speech models. Pricing: free.

Category
Open source
License
MIT
Stars
★ 30.8k
Last push
2025-06-26
Pricing
free
Platforms
Linux, macOS

What it is

A from-scratch C training loop. MIT.

Best for: Studying minimal training loops adaptable to small speech models.
Watch out for: Not an ASR engine.

Install / use

git clone https://github.com/karpathy/llm.c

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported1
HIPAA eligibleNo

Links

GitHub repo ↗

llm.c vs Whipscribe

Featurellm.cWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfree$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages199
PlatformsLinux, macOSWeb, API, MCP

Alternatives to llm.c

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 107.0k
whisper.cpp
Georgi Gerganov

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

OSS · MIT ★ 52.8k
faster-whisper
SYSTRAN

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

OSS · MIT ★ 24.8k

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.