vLLM

by vLLM Project

High-throughput inference engine — supports Whisper / Llava / Qwen-Audio.

TL;DR

High-throughput inference engine — supports Whisper / Llava / Qwen-Audio.

Best for bulk Whisper inference + audio-LLM serving with continuous batching. Pricing: free.

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

What it is

The reference paged-attention inference engine. Apache-2.0.

Best for: Bulk Whisper inference + audio-LLM serving with continuous batching.
Watch out for: GPU-only; Whisper integration newer than text generation paths.

Install / use

pip install vllm

Features

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

vLLM vs Whipscribe

FeaturevLLMWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, DockerWeb, API, MCP

Alternatives to vLLM

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.