ggml

by ggml.ai

The tensor library underneath llama.cpp + whisper.cpp.

TL;DR

The tensor library underneath llama.cpp + whisper.cpp.

Best for building new C/C++ ASR runtimes with INT4/INT5/INT8 quantization. Pricing: free.

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

What it is

The C tensor library powering llama.cpp + whisper.cpp. MIT.

Best for: Building new C/C++ ASR runtimes with INT4/INT5/INT8 quantization.
Watch out for: Lower-level than whisper.cpp itself.

Install / use

git clone https://github.com/ggerganov/ggml

Features

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

ggml vs Whipscribe

FeatureggmlWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOS, WindowsWeb, API, MCP

Alternatives to ggml

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.