Settings
Speech model
The most accurate model for voice agents that demand the highest quality. Best-in-class accuracy with advanced prompting capabilities.
Keyterm Prompting  
Turn silence  100ms – 1000ms
VAD threshold0.4
Interruption delay500ms

Prompt  BETA
Illustration of a messaging/chat interface with speaker labels

Transcribe live audio in real-time

Supported languages:
English
Spanish
German
French
Portuguese
Italian

Click below and start speaking into your microphone. By continuing, you agree to our Playground Terms of Service , Acceptable Use Policy and Privacy Policy.