# Cartesia

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

Category: Productivity. Connect from any Rakazo bot at https://rakazo.com/integrations/cartesia/.

## Actions

- **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** (read-only): Return one pronunciation dictionary and its complete text-to-pronunciation mappings.
- **Get Voice** (read-only): Return synthesis-relevant details for one Cartesia voice by ID.
- **List Accents** (read-only): List supported accents, optionally filtered by language, locale, or voice-localization support.
- **List Agent Models** (read-only): List language models available to Cartesia Managed Agents, including provider, latency, and pricing metadata.
- **List Pronunciation Dictionaries** (read-only): Return one page of pronunciation dictionaries available to the connected account.
- **List Voices** (read-only): Search and filter Cartesia voices, returning one page of voice IDs and synthesis-relevant metadata.
- **Synthesize Speech**: Generate a downloadable audio file from one complete transcript using a selected Cartesia voice.
- **Update Pronunciation Dictionary**: Update a pronunciation dictionary and replace its mappings with the complete supplied item set.