Cartesia
Low-latency text-to-speech (Sonic), voice cloning, voice changing, and speech-to-text (Ink) REST API.
Three ways to use Cartesia
Chat with Geni
Ask Geni to pull data, take actions, or answer questions using this integration in a conversation.
Build a workflow
Create automated workflows that trigger on events, run on a schedule, or chain multiple tools together.
Power an app
Use this integration as a data source or action layer behind a dashboard, form, or internal tool.
Supported tools
Actions your AI agents can perform with Cartesia.
Clone Voice
Create a new voice by cloning from an audio sample.
Create Access Token
Mint a short-lived scoped token for client-side use.
Create Dataset
Create a dataset to hold training audio for fine-tuning.
Create Fine-Tune
Train a custom model from a dataset.
Create Pronunciation Dictionary
Create a dictionary that rewrites text before synthesis.
Delete Dataset
Delete a dataset.
Get started automating Cartesia
Ready-to-use workflows
Prompts using Cartesia
Searchable customer interview library from your Zoom calls
Transcribe your Zoom interviews once, then search every conversation, save quotes by theme, and send them to Notion.
Voiceover request and approval desk for your content team
Your team requests narration, picks a voice, and generates takes in one place, so a reviewer can approve the final audio without a single email thread.
Audio coverage console for your WordPress blog archive
See which of your published posts already have a narrated version, pick the ones that do not, and backfill your whole archive in one run.
Score every sales call and send each rep daily coaching
Every weekday evening, each recorded call gets scored against your QA rubric, logged for managers, and turned into a private coaching note for the rep.
Weekly wins voice recap in Slack from HubSpot deals
Every Friday at 4pm, we turn this week's closed-won HubSpot deals into a warm, celebratory audio recap and drop the mp3 into your #wins Slack channel.
Turn Notion drafts into narrated blog audio and podcast episodes
Every hour, we grab ready-to-narrate Notion drafts, rewrite them for listening, and publish an mp3 to Google Drive with your brand voice.
Nightly voice memo transcription in a Google Drive folder
Every night at 2am, transcribe any new audio in your designated Google Drive folder and drop a text file next to each recording.
Add multilingual audio to every new Webflow blog post
Every 30 minutes, freshly published Webflow posts get translated audio in Spanish, French, and German, uploaded to Drive, and linked back on the post.
