
The TTS (Text-to-Speech) API generates natural, expressive audio from text — dramatically better than older TTS systems.
response = client.audio.speech.create(
model="tts-1",
voice="alloy", # alloy, echo, fable, onyx, nova, shimmer
input="Hello, this is your AI voice assistant."
)
response.stream_to_file("output.mp3")Reference:
TaskLoco™ — The Sticky Note GOAT