Key Metrics
Input Limit
16K tokens
Output Limit
2K tokens
Input Cost
$2.50/1M
Output Cost
$10.00/1M
Sample API Code
Sample Python code not available from this page.Required Libraries
Notes
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.
Capabilities
speech-to-text
audio transcription
language recognition
Supported Data Types
Input Types
audio
text
Output Types
text
Strengths & Weaknesses
Exceptional at
accurate transcription
improved word error rate
enhanced language recognition
high accuracy compared to original Whisper models
Good at
speech-to-text conversion
Additional Information
Latest Update
Jun 1, 2024
Knowledge Cutoff
2024-06-01