Call Cartesia TTS and STT HTTPS/WebSocket APIs with authentication and versioning.
npx skills add https://github.com/cartesia-ai/skills --skill cartesia-api
Please help me install this Agent Skill. Skill: cartesia-api Source: https://github.com/cartesia-ai/skills/tree/main/skills/api Command: npx skills add https://github.com/cartesia-ai/skills --skill cartesia-api
This skill solves the problem of integrating Cartesia speech capabilities—text-to-speech, speech-to-text, and voice selection—into application code and agent-assisted workflows without getting stuck on authentication, versioning, or API conventions.
Use the cartesia-api skill to send a POST request to the Cartesia TTS endpoint with Authorization Bearer set to your Cartesia API key and include the Cartesia-Version header that matches your documentation.
High-intent search queries and answers about installing and using this skill.
Authenticate Cartesia API requests over HTTPS using an Authorization Bearer header with your Cartesia API key. For client applications, generate and use access tokens instead of exposing your primary API key directly.
Cartesia REST HTTPS endpoints handle standard request-response cycles for TTS and STT, while WebSocket APIs support real-time streaming audio. Choose REST for batch processing or WebSocket for low-latency conversational agent workflows.
Include the Cartesia-Version header consistently in all Cartesia TTS and STT HTTPS and WebSocket API calls. The version value must match your documentation to ensure correct endpoint behavior and avoid versioning mismatches.
Yes, Cartesia TTS supports voice management via library, cloning, and localization workflows. Select specific voices in your API requests using API-supported voice identifiers after configuring them through the voice management endpoints.
Yes, the Cartesia API integrates with Python for agent-assisted workflows and optionally supports cartesia-mcp with Python 3.13+. It guides coding agents in choosing REST or SDK paths and handling concurrency or quota errors.
Cartesia TTS streaming requests return concurrency or quota errors when usage limits are exceeded. The skill provides guidance to handle these errors, choose REST versus WebSocket paths, and avoid mixing Cartesia API with Line deployments.
armanisadeghiIntegrate text-to-speech, speech-to-text, and audio playback via Cartesia, Groq PlayAI, and Whisper backends.
wentbackwardClone voices for TTS and transcribe speech via OpenAI-compatible endpoints.
jhd3197Add real-time WebSocket message types and handlers across CachiBot backend and frontend.
skills-routerGenerate speech with voice cloning and transcribe audio to TXT, SRT, or ASS formats.
