← Speech-to-Text

OpenAI

GPT-4o Transcribe

Measured 2026-10-01

Run GPT-4o Transcribe on Speko →

One API, every model on this board.

WER · batch

2.3%

WER · streaming

Read speech

5.64%

Conversation

32.91%

Details

Read speech

n=1541 · FLEURS test+dev+train · vendor-direct

Conversation

28.4–36.9% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01

Finalize

848ms

p50–p90 · US East · n=199 · vendor-direct · ±10%

Time to first token

6.40s

p50–p90 · US East · n=199 · vendor-direct · ±10%

Cost / min

$0.006

Share this result

Embed the live badge

Speko stt rank
Markdown
[![Speko stt rank](https://speko.ai/benchmarks/badge/stt/openai-gpt-4o-transcribe.svg)](https://speko.ai/benchmarks/stt/openai-gpt-4o-transcribe)
HTML
<a href="https://speko.ai/benchmarks/stt/openai-gpt-4o-transcribe"><img src="https://speko.ai/benchmarks/badge/stt/openai-gpt-4o-transcribe.svg" alt="Speko stt rank"></a>
URL
https://speko.ai/benchmarks/stt/openai-gpt-4o-transcribe