Built by Metorial, the integration platform for agentic AI.
Convert text to speech audio using AI voices. Supports multiple text segments with different voices in a single request to create conversational or multi-voice audio. Each segment can have independent SSML controls for pitch, speaking rate, and volume. Returns Base64-encoded audio.
Retrieve the catalog of available text-to-speech voices. Optionally filter by language code to narrow results. Returns voice IDs, display names, and language codes that can be used with the Generate Audio tool.