RETURNN

by RWTH Aachen

RWTH's flexible neural network training framework for ASR research.

Looking at RETURNN? Try this first.

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

TL;DR

Best for academic groups running highly customized E2E ASR experiments. Pricing: free.

What it is

The RWTH Extensible Training Framework for RNNs. RWTHs' speech group ships their CSR systems here. RETURNN public license (MIT-style).

Best for: Academic groups running highly customized E2E ASR experiments.
Watch out for: Steep learning curve; config-file-driven; small community.

Install / use

pip install returnn

Features

Speaker diarization	No
Word-level timestamps	Yes
Streaming / real-time	No
Languages supported	20
HIPAA eligible	No

Links

GitHub repo ↗

RETURNN vs Whipscribe

Feature	RETURNN	Whipscribe
Category	Open source	Transcription APIs
Pricing	free	$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarization	No	Yes
Word timestamps	Yes	Yes
Streaming	No	No
Languages	20	99
Platforms	Linux	Web, API, MCP

Alternatives to RETURNN

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.