Key Metrics
Input Limit
N/A tokens
Output Limit
N/A tokens
Input Cost
$15.00/1M
Output Cost
N/A/1M
Sample API Code
Not provided in the document.Required Libraries
Notes
TTS-1 is a text-to-speech model optimized for speed (rated 'Fast') and realtime use cases, with 'Average' overall performance. It converts text to natural sounding spoken audio. Use with the Speech endpoint (v1/audio/speech) in the Audio API.
Capabilities
text-to-speech
realtime speech synthesis
Supported Data Types
Input Types
Text
Output Types
Audio
Strengths & Weaknesses
Exceptional at
Fast speed
Realtime text-to-speech
Good at
Natural sounding speech generation
Additional Information
Latest Update
Sep 1, 2021
Knowledge Cutoff