New: every message picks a fast or a slow model

Cartesia

Cartesia provides real-time text-to-speech, speech-to-text, voice, model training, and managed voice agent APIs.

What agents can do

Actions10

  • Create pronunciation dictionary

    Create a reusable pronunciation dictionary for text-to-speech generation.

  • Delete pronunciation dictionary

    Permanently delete one pronunciation dictionary by ID.

  • Get pronunciation dictionary

    Return one pronunciation dictionary and its complete text-to-pronunciation mappings.

  • Get voice

    Return synthesis-relevant details for one Cartesia voice by ID.

  • List accents

    List supported accents, optionally filtered by language, locale, or voice-localization support.

  • List agent models

    List language models available to Cartesia Managed Agents, including provider, latency, and pricing metadata.

  • List pronunciation dictionaries

    Return one page of pronunciation dictionaries available to the connected account.

  • List voices

    Search and filter Cartesia voices, returning one page of voice IDs and synthesis-relevant metadata.

2 more
  • Synthesize speech

    Generate a downloadable audio file from one complete transcript using a selected Cartesia voice; usage is billed by transcript length.

  • Update pronunciation dictionary

    Update a pronunciation dictionary and replace its mappings with the complete supplied item set.

How it connects

You paste an API key from Cartesia on a page Composio hosts, so the key never passes through Definable.

Keep the connection to yourself or share it with your workspace. Any action that writes or sends can wait for your approval.