AudioMAE

by Meta AI

Masked-Autoencoder pretrain for audio — feeds downstream ASR.

Looking at AudioMAE? Try this first.

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

Upstream is archived. AudioMAE’s repository has been set read-only by its owner, so there are no further releases, fixes, or security patches. The last commit landed 2024-04-05. It can still be cloned and run, and forks may be maintained elsewhere. See the repository.

TL;DR

Best for self-supervised audio pretraining baselines. Pricing: free.

Category
Open source
License
NOASSERTION
Stars
★ 672
Last push
2024-04-05
Pricing
free
Platforms
Linux

What it is

The AudioMAE paper code. CC-BY-NC-4.0 — non-commercial.

Best for: Self-supervised audio pretraining baselines.
Watch out for: Research; not a turnkey ASR engine.

Install / use

Features

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

Links

GitHub repo ↗

AudioMAE vs Whipscribe

FeatureAudioMAEWhipscribe
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
PlatformsLinuxWeb, API, MCP

Alternatives to AudioMAE

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.