Cartesia

Documented custom tool support. Managed Agents take webhook tools, where Cartesia sends the HTTPS request to an endpoint the customer exposes, client tools that run in the customer's app over the WebSocket, and system tools for ending a call, sending DTMF and transferring to a phone number, up to 32 tools per agent, so an agent can look up an order or trigger an action during a call. Plugins for LiveKit, Pipecat and other voice stacks distribute Cartesia's models and are not agent integrations.

SourceCartesia, docs.cartesia.ai (Tools, Webhook tools, Integrations)read 2026-09-27

A fixed agent loop that Cartesia runs. A Managed Agent combines Ink-2 listening, the chosen LLM and Sonic speech with turn taking, interruptions and tool calls, and each configuration change is saved as a version; no workflow graph, branching model or hand off between agents is documented for Managed Agents, and the older Line SDK is being migrated away from.

SourceCartesia, docs.cartesia.ai (Managed Agents, Agent configuration, Migrate from the Line SDK)read 2026-09-27

A maintained index over the customer's documents. Documents uploaded through the Playground or the documents API (single or bulk, up to 100 a request) are indexed automatically on upload, organized into nested folders with metadata for filtering, and an agent's queries search only the folders attached to it; documents can be updated or deleted through the API.

SourceCartesia, docs.cartesia.ai (Knowledge Base, Create Document API)read 2026-09-27

A human handoff in one place. The transfer system tool hands the caller to a phone number, and turn settings end or check in on silent calls; the configuration's Guardrails are rules written into the agent's instructions, which is prompting, not an enforced control, and no approval step holds a tool call for a person.

SourceCartesia, docs.cartesia.ai (Agent configuration, System tools)read 2026-09-27

Access and compliance are both documented. On access, Enterprise organizations get self serve SSO over SAML or OIDC, configured by an organization admin, and Admin and Member roles, where only admins manage members, invitations and settings. On compliance, the pricing page FAQ states Cartesia is SOC 2 Type II certified, and a Vanta trust center sits at trust.cartesia.ai; Zero Data Retention is available on Enterprise.

SourceCartesia, docs.cartesia.ai (Set up SSO, Set up an organization) and cartesia.ai/pricingread 2026-09-27

Run level records of what each agent did. Every call has a transcript with turn level timestamps and call logs with the agent's logging statements, custom events can be recorded, runtime logs are retrievable through the API, and webhooks deliver call and turn events carrying each turn's tool calls, variable updates and speech latency, plus a post call analysis.

SourceCartesia, docs.cartesia.ai (Observability, Get Call Runtime Logs)read 2026-09-27

Conversation state lives inside a call. Within a call the agent keeps the conversation, and dynamic variables set at the start or changed by tools are read by the agent each time it responds; nothing carries into the next call except what the customer passes in as variables, and no memory layer with a scope and lifetime is documented.

SourceCartesia, docs.cartesia.ai (Agent configuration, Dynamic variables)read 2026-09-27

Named regions offered as an option, plus customer environments by arrangement. Enterprise customers can use dedicated regional deployments in the United States, European Union, United Kingdom, India and Australia that keep inference traffic in region; the homepage states the same models and agents run cloud, on premise and on device, and the pricing FAQ routes on premise and VPC deployment through sales.

SourceCartesia, docs.cartesia.ai (Regional endpoints) and cartesia.ai (home, pricing FAQ)read 2026-09-27

Starting templates exist; what they contain is not documented. The agents API lists public, Cartesia provided agent templates to help a customer get started, but no docs page names a template or what job it does, and nothing shows a whole agent a buyer adopts; the voice library, multilingual voices and pinned model snapshots are model assets, not agents.

SourceCartesia, docs.cartesia.ai (List Templates API reference)read 2026-09-27

A scheduled wake plus phone and app channels. A call batch stores up to 5,000 recipients and Cartesia dials them in the background, at a scheduled_at time when one is set, up to a concurrency limit, with retries for failed calls; agents also take inbound and outbound calls on Cartesia or Twilio numbers and SIP trunks, and stream over a WebSocket from web and mobile apps.

SourceCartesia, docs.cartesia.ai (Batch calling, Phone numbers, WebSocket API)read 2026-09-27

The customer chooses the model. Each agent's config sets the LLM by ID from the list GET /v1/agents/models returns, with provider, average latency and token prices shown, plus temperature and output limits; changing it creates a new version so candidates can be compared. Cartesia manages the provider accounts, and speech in and out uses Cartesia's own Ink and Sonic models.

SourceCartesia, docs.cartesia.ai (LLMs, Agent configuration)read 2026-09-27

A documented API and SDKs for Cartesia's own platform. A versioned REST API (214 reference pages, published OpenAPI and AsyncAPI specs) covers text to speech, speech to text, voices and agents, including agents, tools, knowledge base documents, call batches, metrics and webhooks; official JavaScript and TypeScript and Python SDKs, a CLI, and an MCP server that runs TTS, STT, voices and pronunciation dictionaries sit beside it.

SourceCartesia, docs.cartesia.ai (llms.txt, Client Libraries, MCP)read 2026-09-27

Scoring of live calls, without a test harness or gate. Cartesia scores completed calls with built in metrics (call success, speech latency) and custom LLM as a judge metrics the customer writes and assigns to an agent, with results exportable, so output quality can be tracked over time. No fixture or dataset testing before production, quality gate or tuning loop is documented.

SourceCartesia, docs.cartesia.ai (Metrics, Results)read 2026-09-27

The DTMF system tool presses phone keys, which is not browser or desktop control, and the browser examples stream voice into a web page, the product running in a browser. No browser, desktop or computer control is documented.

SourceCartesia, docs.cartesia.ai (llms.txt, System tools)read 2026-09-27