GPT-4o Transcribe
v2025-03-20
by OpenAI • Released Mar 20, 2025
Description
GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.
Use Cases
Languages
Specifications
- Context Length
- 16.0K
- Pricing
- Input: $2.50 / 1M tokens
Output: $10.00 / 1M tokens - License
- commercial
Provider
OpenAI
AI Model Provider