TTS-1
Author
OpenAI
OpenAIContext—
Tool calling
TTS-1 is OpenAI's text-to-speech model optimized for real-time, low-latency use, converting text to natural sounding spoken audio.
Tokens, last 14 days
No usage yet
Prompt—
Completion—
Total—
Performance
Latency (p50)—
Throughput (p50)—
Pricing
Speech$0.0075/1k chars
Features
Inputtext
Outputaudio
APISpeech
Vision