# Cartesia — Real-time speech models and a managed runtime for production phone and web voice agents.

> Source: The Agents Index — https://theagentsindex.com/cartesia (structured, researched, re-verified)
> Facts last verified: 2026-09-02

Cartesia is a voice AI platform whose Sonic text-to-speech and Ink speech-to-text models power a managed runtime for realtime phone and web voice agents. Agents are configured with instructions, a chosen LLM, tools and telephony, then deployed on Cartesia's infrastructure.

| Fact | Value |
| --- | --- |
| Website | https://cartesia.ai |
| Price | from $5/month |
| Free tier | Yes |

$0/mo: 20K credits/month (~27 TTS minutes, ~1h51m of Ink-2 STT), $1 prepaid agent dollars (~17 agent minutes at $0.06/min), 2 TTS and 8 STT concurrent requests, 1 Cartesia phone number, no commercial-use licence, no voice cloning, organization limited to one member.

## What it does

**Writes code** · No — The vendor positions itself as a voice model and voice agent lab; no surface authors application code.

> Cartesia is an AI lab building real-time voice models and agents.
> — https://docs.cartesia.ai/get-started/overview · Welcome to Cartesia, opening line

**Debugs and fixes** · No — Its debugging surface is call logs for conversations, not diagnosis or repair of source code.

> Call logs – Debug conversations and monitor performance
> — https://docs.cartesia.ai/line/introduction · Developer Tools list, Call logs bullet

**Writes tests** · No — The evaluations framework scores live calls against metrics you define; it produces no test code.

> How do you know your voice agent is any good? We added a framework for live testing, system metrics, and custom call analytics.
> — https://www.cartesia.ai/agents · Built-in evaluations section

**Reviews code** · No — Nothing in the product or docs reviews a diff; the reviewed artefact is a call, not a change set.

> Cartesia is an AI lab building real-time voice models and agents.
> — https://docs.cartesia.ai/get-started/overview · Welcome to Cartesia, opening line

**Whole-codebase work** · No — Retrieval is over document folders you upload, not over a source repository, so no migration can be carried across one.

> Knowledge bases let you augment your agent with domain-specific information it can retrieve on the fly.
> — https://docs.cartesia.ai/line/knowledge-base · Opening paragraph

**Ships it** · Partly — The CLI deploys the agent code you wrote to Cartesia's cloud; the product itself produces no diffs to ship.

> Deploy your agent to Cartesia cloud.
> — https://docs.cartesia.ai/line/cli · CLI documentation, Commands > Voice Agents, cartesia deploy

**Done-for-you service** · No — Self-serve software: you build and deploy the agent yourself; sales contact exists for Enterprise terms, not for building it for you.

> Start building. Access our models via API and bring a voice agent into production in minutes.
> — https://www.cartesia.ai/agents · 'Get started today' section, second card

## How much it does unattended

**Runs autonomously** · Yes — A deployed agent runs a whole call unattended, handling turn-taking, interruptions and tool calls; it transfers to a human only when a configured condition matches.

> Your agent handles turn-taking and interruptions, streams audio, and can use tools during a conversation.
> — https://docs.cartesia.ai/agents/introduction · Introduction, opening paragraph

**Multi-agent** · No — System tools enumerate three slots: end call, DTMF, and transfer to an E.164 phone number. An agent therefore hands off to a number, not to another Cartesia agent.

> `config.system_tools` currently supports three slots: `end_call`, `send_dtmf`, and `transfer_to_number`.
> — https://docs.cartesia.ai/agents/system-tools · System tools, first paragraph

**Agent permissions** · Partly — Limits are prompt-level guardrails plus per-tool execution settings (timeout, immediate vs async, speak-before-acting); there is no separate policy engine.

> # Guardrails Never invent order details. Ask for an order number before using the lookup tool.
> — https://docs.cartesia.ai/agents/configuration · Instructions and greeting, prompt structure example

## Which models it runs on

**Claude** · Yes — Anthropic Claude models are named in the SDK's supported-models table and used in its examples.

> Anthropic | anthropic/claude-haiku-4-5-20251001, anthropic/claude-sonnet-4-5
> — https://docs.cartesia.ai/line/sdk/agents · LlmAgent > Supported Models table, Anthropic row

**GPT** · Yes — OpenAI GPT models appear in the same supported-models table.

> OpenAI | gpt-5.4, gpt-5.2
> — https://docs.cartesia.ai/line/sdk/agents · LlmAgent > Supported Models table, OpenAI row

**Open models** · Partly — The LLM layer routes through LiteLLM to 100+ providers, but the vendor names only Anthropic, OpenAI and Google, and its own speech models are API-only.

> And 100+ more via LiteLLM
> — https://docs.cartesia.ai/line/sdk/agents · LlmAgent > Supported Models table, final row

**Model choice** · Yes — You pick the agent's LLM and can swap it in the Playground or API; Cartesia owns the speech models and manages the LLM integration.

> Cartesia manages the model integration, so you do not need a provider account or API key.
> — https://docs.cartesia.ai/agents/models · LLMs, opening line

## Where you use it

**In your editor** · Partly — No native IDE extension; the documented editor surface is the Cartesia MCP server used from Cursor or Claude Code.

> Use **Cartesia MCP** in **Cursor**, **Claude Code**, or other MCP clients to list voices, run TTS and STT, manage pronunciation dictionaries, download cloud-stored generations, and more
> — https://docs.cartesia.ai/tools/ai/mcp · MCP, opening paragraph

**On the command line** · Yes — A `cartesia` CLI creates, deploys and manages agents, and can chat with agent logic locally.

> Create, deploy, and manage voice agents from the command line.
> — https://docs.cartesia.ai/line/cli · CLI documentation, subtitle

**In your pipeline** · Partly — Deployments can be triggered by pushing to a linked GitHub repository, but there is no pull-request or CI review surface.

> Use `cartesia deploy` or push to a linked GitHub repository to create a deployment.
> — https://docs.cartesia.ai/line/infrastructure/deployments · Creating a deployment

**In a browser** · Yes — The Playground is the hosted surface for creating, configuring and testing agents and models.

> Create and test an agent in the [Playground](https://play.cartesia.ai/agents), or manage the same agents through the [API](/api-reference/agents/create).
> — https://docs.cartesia.ai/agents/introduction · Introduction, second paragraph

## Whose machine it runs on

**Self-hosted** · Partly — On-premise or VPC model deployment is sales-gated; separately, agent reasoning code can run on your own servers with Cartesia connecting to your URL.

> Yes, reach out to our sales team so we can best understand your needs.
> — https://www.cartesia.ai/pricing · Pricing FAQ, 'Can I deploy the models on-premise or in a virtual private cloud?'

**Open source** · Partly — The official JS/TS and Python client SDKs are public repositories on Cartesia's GitHub; the Sonic and Ink models and the agent runtime are not.

> Use the official Cartesia SDKs to call TTS, STT, and voice APIs from JavaScript/TypeScript or Python.
> — https://docs.cartesia.ai/tools/client-libraries · Client Libraries, opening line

## What it costs to run

**How it meters** · Yes — Two meters: credits for the models (about 1 credit per TTS character, 3 credits per second of Ink-2 audio) and per-minute US dollars for agent calls.

> Cartesia meters model usage in **credits** and agent usage in **agent dollars**.
> — https://docs.cartesia.ai/pricing · Pricing, opening line

**Free tier** · Yes — A $0/month plan with 20K credits and $1 of prepaid agent usage, signed up for without a call.

> Free $0 /mo Start free 20K credits / month $1 prepaid agents / month
> — https://www.cartesia.ai/pricing · Plan cards, Free column

**API access** · Yes — REST and WebSocket APIs cover TTS, STT and agent management, with official Python and JS SDKs.

> API conventions, errors, and the reference for every REST and WebSocket endpoint.
> — https://docs.cartesia.ai/get-started/overview · Start building cards, 'API reference'

**MCP server** · Yes — A hosted MCP server (mcp.cartesia.ai) exposes tools for TTS, STT, voices, cloning and credit usage to another agent.

> Pick your client, install, and sign in when prompted. A **Cartesia MCP** API key is created for your organization if one does not exist yet.
> — https://docs.cartesia.ai/tools/ai/mcp · MCP, Setup

**Bring your own key** · Partly — No bring-your-own LLM key: Cartesia bills the LLM itself. You can bring your own carrier via SIP trunking and host the agent's reasoning code yourself.

> Cartesia manages the model integration, so you do not need a provider account or API key.
> — https://docs.cartesia.ai/agents/models · LLMs, opening line

## Buying it for a team

**A company can buy it** · Yes — Organization workspaces with their own billing, plus an Enterprise plan carrying DPAs and BAAs.

> Organization workspaces enable seamless collaboration between multiple team members. All users in an organization share the same view of resources, including voices, API keys, and datasets.
> — https://docs.cartesia.ai/enterprise/set-up-an-organization · Set up an organization, opening paragraph

**Seat model** · Partly — Seats are not priced, but inviting anyone requires Startup ($49/mo) or above; a Free organization is capped at one member. The pricing page's 'unlimited workspace seats on every plan' contradicts this.

> To invite team members, you must first upgrade your organization to the Startup tier or higher. After upgrading, you can invite unlimited users at no additional cost.
> — https://docs.cartesia.ai/enterprise/set-up-an-organization · Warning callout above 'Manage your organization'

**Pooled budget** · Yes — Credits and prepaid agent dollars belong to the workspace, and every member shares the same resources and balance.

> Each workspace has its own billing and credit limits, so make sure you are on the intended organization before proceeding to upgrade your subscription.
> — https://docs.cartesia.ai/enterprise/set-up-an-organization · Step 'Upgrade your current organization'

**Admin controls** · Partly — Roles are Admin and Member only: an admin controls the org, invitations and members, not what an agent is permitted to do at runtime.

> 1. Admin: has the ability to manage the organization profile, invitations, and members. 2. Member: can use all functionality included in the subscription, but cannot alter organization settings.
> — https://docs.cartesia.ai/enterprise/set-up-an-organization · Step 'Invite your team', membership types

**Audit log** · Partly — Deployment logs, call logs and transcripts are recorded per agent; no administrative audit trail of account actions is documented.

> You can click into a call and view any logging statements generated by your reasoning code.
> — https://docs.cartesia.ai/line/infrastructure/observability · Call Logs section

**Single sign-on** · Partly — SAML and OIDC, self-serve from the Playground, but only on the Enterprise plan and only for an organization admin.

> SSO is available on the **Enterprise** plan, and only an **organization admin** can configure it.
> — https://docs.cartesia.ai/enterprise/set-up-sso · Note callout, Set up SSO

## What happens to your code

**Opt out of training** · Partly — Opt-out is by request form for selected categories of content; Enterprise plans can additionally enable Zero Data Retention for TTS and STT inference.

> You may request that we not use certain categories of your Content to train our models by completing this online form.
> — https://www.cartesia.ai/legal/privacy · Section 3, 'Use of Information'

**Data residency** · Partly — By default api.cartesia.ai routes to the nearest endpoint; pinned regional deployments (US, EU, UK, India, Australia) are Enterprise-only.

> Dedicated regional deployments are available to Cartesia Enterprise customers to support data sovereignty requirements.
> — https://docs.cartesia.ai/enterprise/regional-endpoints · Regional endpoints, subtitle

**Getting out** · Partly — Purchased credits survive tier changes and cancellation, but rollover is capped at 2x the monthly plan rate; call transcripts export via API or CLI.

> You will keep the credits in your account until you use them. Your account will remain in the same tier until the end of that period, at which time you will automatically be downgraded to the selected tier.
> — https://www.cartesia.ai/pricing · Pricing FAQ, 'What if I cancel or downgrade my tier in the middle of a payment period?'

**Certifications** · Yes — GDPR, SOC 2 Type II, HIPAA and PCI-DSS service provider, with a public Trust Center; DPAs and BAAs come with Enterprise.

> Cartesia is GDPR, SOC 2 Type II, PCI-DSS service provider, and HIPAA compliant.
> — https://docs.cartesia.ai/enterprise/zero-data-retention · Zero Data Retention, Overview

## Provenance

Every fact above comes from the vendor. Nothing here is independently corroborated yet.

## Coverage elsewhere

Pages about this product that the vendor does not control. The label states how independent each one is.

| Source | Kind | Read |
| --- | --- | --- |
| research.contrary.com | Independent source | 2026-08-05 |

## What changed

- 2026-09-02 — Capabilities · Commercial terms · Free tier
- 2026-08-31 — Capabilities · Commercial terms · Free tier · Price
- 2026-08-23 — Alternatives

## Correcting this record

Anything marked "Not established" is a question we have not answered — it is not a No. If you represent Cartesia, or anything here is wrong or out of date, you can supply it with a source: the operations this site accepts from an agent are listed at https://theagentsindex.com/.well-known/agents.json — that catalogue needs no key to read, and each entry states its own auth.

Supplying evidence is free. Nothing that can be bought here changes what a field says, whether a gap is closed, or how this record is scored.