Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | openaiOpenAI: GPT TranscribeRemove × |
|---|---|
| What’s different | GPT Transcribe is a high-accuracy speech-to-text model from OpenAI. It is suited for recorded audio, streamed file transcription, and committed Realtime turns, with free-form context, keyword hints, and… |
| Date | Aug 5, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $75.00 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → |
Benchmarks Each result retains its evaluation configuration | |
| AMI-Cleaned WER ↗English short-form; normalization unversioned | 8.95% WER ↗openai/gpt-transcribeLeaderboard entry |
| Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned | 6.61% WER ↗openai/gpt-transcribeLeaderboard entry |
| Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned | 7.76% WER ↗openai/gpt-transcribeLeaderboard entry |
| LS Clean WER ↗English short-form; normalization unversioned | 1.31% WER ↗openai/gpt-transcribeLeaderboard entry |
| LS Other WER ↗English short-form; normalization unversioned | 3.39% WER ↗openai/gpt-transcribeLeaderboard entry |
| SPGISpeech WER ↗English short-form; normalization unversioned | 2.23% WER ↗openai/gpt-transcribeLeaderboard entry |
| URGENT2024 WER ↗English short-form; normalization unversioned | 12.86% WER ↗openai/gpt-transcribeLeaderboard entry |
| Voice Arena Monsoon WER ↗English short-form; normalization unversioned | 3.63% WER ↗openai/gpt-transcribeLeaderboard entry |
| Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned | 2.65% WER ↗openai/gpt-transcribeLeaderboard entry |
Specifications | |
| Context window | — |
| Max output | — |
| Parameters | — |
| Audio input | Supported |
| Transcription | Supported |