paper-qa

by Future-House

RAG over PDFs / transcripts — downstream ASR consumer pattern.

TL;DR

RAG over PDFs / transcripts — downstream ASR consumer pattern.

Best for pipelines that ingest Whisper transcripts into research-grade QA. Pricing: free.

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

What it is

A reference RAG pipeline over PDF + transcript corpora. Apache-2.0.

Best for: Pipelines that ingest Whisper transcripts into research-grade QA.
Watch out for: Not an ASR engine.

Install / use

pip install paper-qa

Features

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

paper-qa vs Whipscribe

Featurepaper-qaWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsLinux, macOSWeb, API, MCP

Alternatives to paper-qa

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.