GENAIWIKI

OpenAI

Whisper large-v3

Speech-to-text · Release Nov 6, 2023 · MIT

Robust ASR model for transcription and translation with strong performance across accents and noisy environments.

audioopen-weightsedge
Updated today

Modalities

What goes in and what comes out.

Inputs

audio

Outputs

text

Capabilities

transcription, translation, timestamps

Benchmarks snapshot

Structured JSON for reproducible comparisons.

{
  "wer": "low on common benchmarks"
}

Related on GenAIWiki

Same provider, tooling that cites the model, or prompts tuned for it.