← Speech-to-Text

OpenAI

GPT Live Transcribe

Measured 2026-10-01

Run GPT Live Transcribe on Speko →

One API, every model on this board.

WER · batch

—

Streaming-only endpoint

WER · streaming

Read speech

4.89%

Conversation

13.53%

Details

Read speech

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

Conversation

11.3–16.0% · EdAcc n=283 · 60 speakers, 2 passes, 2026-10-01

Finalize

620ms

p50–p90 · US East · n=200 · vendor-direct · re-measured 2026-09-15 · ±3%

Measured 2026-09-15

Time to first token

1.72s

p50–p90 · US East · n=200 · vendor-direct · re-measured 2026-09-15 · ±4%

Measured 2026-09-15

Cost / min

$0.017

gpt-live-transcribe, the streaming path this row is recommended for.

Share this result

Embed the live badge

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