Skip to main content
The speak capability converts text to natural-sounding speech using neural voice synthesis.

Providers

Basic Usage

Parameters

string
required
The text to convert to speech.
string
Voice ID or name. Default varies by provider.
string
TTS model to use.

Response

Examples

With Specific Voice

Generate Podcast Narration

Multi-Section Audio

Pricing

Download Audio

Text Length Limits

Very long texts may be split into multiple requests. Consider chunking long content to manage costs.