RAVDESS

by Ryerson University

Audio-visual emotional speech + song corpus — open SER benchmark.

TL;DR

Audio-visual emotional speech + song corpus — open SER benchmark.

Best for open speech-emotion recognition with audio + video. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
Zenodo

What it is

RAVDESS provides 7356 audio + video files from 24 actors expressing 8 emotions (calm, happy, sad, angry, fearful, surprise, disgust, neutral). License: CC BY-NC-SA 4.0.

Best for: Open speech-emotion recognition with audio + video.
Watch out for: CC BY-NC-SA 4.0 · NON-COMMERCIAL · 24 actors · 8 emotion classes. Cite: Livingstone & Russo, PLOS ONE 2018.

Install / use

https://zenodo.org/record/1188976

Features

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

RAVDESS vs Whipscribe

FeatureRAVDESSWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsNoYes
StreamingNoNo
Languages199
PlatformsZenodoWeb, API, MCP

Alternatives to RAVDESS

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.