[api设置] TTS Voice API: Introduction and Usage Guide

What is it?
With the new text-to-speech API, developers can generate high-quality spoken audio from text. OpenAI initially offers six preset voices to choose from and provides two model variants, tts-1 and tts-1-hd. tts-1 is optimized for real-time use cases, and tts-1-hd is optimized for quality. Pricing starts at $0.015 per 1,000 input characters (not tokens).

How do I use it?
Anyone with an OpenAI API account can access the new audio/speech endpoint.

What rate limits can I expect?
Rate limits for paid accounts start at 50 RPM. You can view your limits in the developer console.

What is the maximum input size that can be submitted per request?
4096 characters (equivalent to about 5 minutes of audio at default speed).

Can audio be streamed?
Yes! By setting stream=True, you can chunk the returned audio file.