openai/tts-1/text-to-speechOpenAI's TTS-1 is a speech model built for fast, low-latency output: it reads up to 4,096 characters aloud in nine preset voices, with speaking speed adjustable from 0.25× to 4× and MP3, Opus, AAC, FLAC, WAV or PCM files.
From $0.003/1,000 characters80% below the publisher's list price
Workbench
Loading
