Built by Metorial, the integration platform for agentic AI.
Convert text to speech audio using AI voices. Combine multiple text segments and voices in a single request, with independent pitch, speaking rate, and volume controls. Provides a downloadable audio file and the original Base64 audio for existing workflows.
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.
Check a speech recognition job from create_transcription. Completed jobs provide downloadable plain-text transcripts and SRT subtitles. Pending jobs report their current status.
Submit an MP3, WAV, FLAC, or OGG audio file for speech recognition. Returns a job ID; call get_transcription to check progress and download the completed transcript and subtitles.