> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/integrations/catalog/cartesia.md).

# Cartesia

Generate speech, browse voices, and clone or localize voices with Cartesia.

### Connectors

Choose the connector that matches your authentication method. The options below use the names shown in StackAI.

| Connector          | Authentication |
| ------------------ | -------------- |
| Cartesia (API Key) | API Key        |

#### Cartesia (API Key)

Connect to Cartesia with an API key to generate speech and manage voices.

**Set up in Cartesia**

1. Prepare the Cartesia account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Your Cartesia API key (starts with sk\_car\_). Create one at play.cartesia.ai/keys.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Cartesia (API Key)**.
2. Enter the credentials and connection details in the fields below.
3. Save the connection and check its connection status. Select this saved connection when configuring an action or feature that uses it.

**Connection fields**

| StackAI field | Required | What to enter                                                                                                                               |
| ------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
| API Key       | Yes      | Your Cartesia API key (starts with sk\_car\_). Create one at play.cartesia.ai/keys. [Provider instructions](https://play.cartesia.ai/keys). |

#### Verify the connection

Check that the connection is healthy. Then run a read operation against a resource the connected account can access. A successful connection check confirms authentication; it does not guarantee permission for every action.

If access is denied, check the credential or OAuth permissions, the selected account or environment, and access to the specific resource. Update expired credentials or reconnect after permissions change.

### Use an action

1. Add the required **Cartesia** action to the workflow.
2. Select a connection when the action requests one.
3. Complete the required fields. Use the reference picker when a value comes from another workflow step.
4. Run the workflow and inspect the action’s output. Check the result before using it in a later step.

### Actions

#### Generate Speech

Turn text into natural-sounding speech with a Cartesia voice and get a downloadable audio file.

**Inputs**

| Field        | Type             | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
| ------------ | ---------------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Text         | textarea         | Yes      | The text you want spoken aloud.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |
| Voice        | select (string)  | Yes      | The voice that reads the text. Options load from the selected connection.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
| Model        | select (string)  | No       | The Sonic model that generates the audio. Available values: Sonic 3.5 (stable), Sonic 3, Sonic Latest. Default: sonic-3.5.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
| Audio Format | select (string)  | No       | The file type of the generated audio. Available values: MP3 (128 kbps), WAV (16-bit PCM). Default: mp3.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
| Language     | select (string)  | No       | The language the text is written in. Leave empty to use the voice's language. Available values: English (en), French (fr), German (de), Spanish (es), Portuguese (pt), Chinese (zh), Japanese (ja), Hindi (hi), Italian (it), Korean (ko), Dutch (nl), Polish (pl), Russian (ru), Swedish (sv), Turkish (tr), Tagalog (tl), Bulgarian (bg), Romanian (ro), Arabic (ar), Czech (cs), Greek (el), Finnish (fi), Croatian (hr), Malay (ms), Slovak (sk), Danish (da), Tamil (ta), Ukrainian (uk), Hungarian (hu), Norwegian (no), Vietnamese (vi), Bengali (bn), Thai (th), Hebrew (he), Georgian (ka), Indonesian (id), Telugu (te), Gujarati (gu), Kannada (kn), Malayalam (ml), Marathi (mr), Punjabi (pa), Odia (or), Urdu (ur). |
| Sample Rate  | select (integer) | No       | Audio quality in Hz. Use 8000 for phone lines. Available values: 8,000 Hz, 16,000 Hz, 22,050 Hz, 24,000 Hz, 44,100 Hz, 48,000 Hz. Default: 44100.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
| Speed        | number           | No       | How fast the voice speaks, from 0.6 (slower) to 1.5 (faster).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
| Volume       | number           | No       | How loud the voice is, from 0.5 (quieter) to 2.0 (louder).                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
| Emotion      | select (string)  | No       | An emotional tone for the delivery. Available values: Neutral, Happy, Excited, Enthusiastic, Elated, Euphoric, Triumphant, Amazed, Surprised, Flirtatious, Curious, Content, Peaceful, Serene, Calm, Grateful, Affectionate, Trust, Sympathetic, Anticipation, Mysterious, Angry, Mad, Outraged, Frustrated, Agitated, Threatened, Disgusted, Contempt, Envious, Sarcastic, Ironic, Sad, Dejected, Melancholic, Disappointed, Hurt, Guilty, Bored, Tired, Rejected, Nostalgic, Wistful, Apologetic, Hesitant, Insecure, Confused, Resigned, Anxious, Panicked, Alarmed, Scared, Proud, Confident, Distant, Skeptical, Contemplative, Determined.                                                                                  |

**Outputs**

| Field           | Type     | Description                           |
| --------------- | -------- | ------------------------------------- |
| File            | object   | The stored audio file.                |
| Signed URL      | string   | Temporary link to download the audio. |
| Expiration Date | datetime | When the download link stops working. |

#### List Voices

Browse or search the voices available to your Cartesia account.

**Inputs**

| Field             | Type            | Required | Description                                                                                            |
| ----------------- | --------------- | -------- | ------------------------------------------------------------------------------------------------------ |
| Search            | string          | No       | Find voices by name, description, or ID.                                                               |
| Only My Voices    | boolean         | No       | Show only voices your organization created, such as clones. Default: false.                            |
| Gender            | select (string) | No       | Only show voices with this gender presentation. Available values: Masculine, Feminine, Gender Neutral. |
| Language          | string          | No       | Only show voices for this language or locale.                                                          |
| Max Results       | integer         | No       | How many voices to return. Minimum: 1. Maximum: 100. Default: 25.                                      |
| Start After Voice | string          | No       | Continue a previous list from where it stopped.                                                        |

**Outputs**

| Field       | Type          | Description               |
| ----------- | ------------- | ------------------------- |
| Voices      | object\_array | The matching voices.      |
| Next Cursor | string        | Use to fetch more voices. |

#### Get Voice

Look up the details of one Cartesia voice.

**Inputs**

| Field | Type            | Required | Description                                                      |
| ----- | --------------- | -------- | ---------------------------------------------------------------- |
| Voice | select (string) | Yes      | The voice to look up. Options load from the selected connection. |

**Outputs**

| Field | Type   | Description        |
| ----- | ------ | ------------------ |
| Voice | object | The voice details. |

#### Clone Voice

Create a new custom voice from a short recording of someone speaking; only clone a voice with that speaker's consent.

**Inputs**

| Field          | Type            | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
| -------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Audio Clip URL | string          | Yes      | Public link to a clear recording of one speaker (up to 16 MB).                                                                                                                                                                                                                                                                                                                                                                                                             |
| Voice Name     | string          | Yes      | A name for the new voice.                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| Language       | select (string) | Yes      | The language spoken in the recording. Available values: English, French, German, Spanish, Portuguese, Chinese, Japanese, Hindi, Italian, Korean, Dutch, Polish, Russian, Swedish, Turkish, Tagalog, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian, Hungarian, Norwegian, Vietnamese, Bengali, Thai, Hebrew, Georgian, Indonesian, Telugu, Gujarati, Kannada, Malayalam, Marathi, Punjabi, Odia, Urdu. Default: en. |
| Description    | textarea        | No       | Notes about the voice.                                                                                                                                                                                                                                                                                                                                                                                                                                                     |
| Tagline        | string          | No       | A few words describing the voice (max 32 characters).                                                                                                                                                                                                                                                                                                                                                                                                                      |
| Accent         | select (string) | No       | Accent name that matches the language, such as British English. Options load from the selected connection.                                                                                                                                                                                                                                                                                                                                                                 |
| Base Voice     | select (string) | No       | An existing voice the clone is derived from. Options load from the selected connection.                                                                                                                                                                                                                                                                                                                                                                                    |

**Outputs**

| Field | Type   | Description    |
| ----- | ------ | -------------- |
| Voice | object | The new voice. |

#### Localize Voice

Create a copy of a voice that speaks another language.

**Inputs**

| Field                   | Type            | Required | Description                                                                                                                                                                                                                                                                                                                      |
| ----------------------- | --------------- | -------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Source Voice            | select (string) | Yes      | The voice to adapt. Options load from the selected connection.                                                                                                                                                                                                                                                                   |
| Target Language         | select (string) | Yes      | The language the new voice speaks. Available values: English (en), German (de), Spanish (es), French (fr), Japanese (ja), Portuguese (pt), Chinese (zh), Hindi (hi), Italian (it), Korean (ko), Dutch (nl), Polish (pl), Russian (ru), Swedish (sv), Turkish (tr), Arabic (ar), Hebrew (he), Tamil (ta), Telugu (te), Thai (th). |
| Original Speaker Gender | select (string) | Yes      | The gender of the speaker in the source voice. Available values: Male, Female.                                                                                                                                                                                                                                                   |
| New Voice Name          | string          | Yes      | A name for the new voice.                                                                                                                                                                                                                                                                                                        |
| Description             | textarea        | Yes      | Notes about the new voice.                                                                                                                                                                                                                                                                                                       |
| Accent                  | select (string) | No       | Accent of the new voice. Leave empty for the language default. Options load from the selected connection.                                                                                                                                                                                                                        |

**Outputs**

| Field | Type   | Description              |
| ----- | ------ | ------------------------ |
| Voice | object | The new localized voice. |

#### Delete Voice

Permanently delete a voice your organization created.

**Inputs**

| Field | Type            | Required | Description                                                                                         |
| ----- | --------------- | -------- | --------------------------------------------------------------------------------------------------- |
| Voice | select (string) | Yes      | The voice to delete. Only voices you created are listed. Options load from the selected connection. |

**Outputs**

| Field    | Type    | Description                    |
| -------- | ------- | ------------------------------ |
| Voice ID | string  | The deleted voice.             |
| Deleted  | boolean | Whether the voice was deleted. |

### Important behavior

Actions that create, update, send, or delete data can change the connected service. Review their inputs before running them. A retry can repeat an operation; consider this when configuring retries for actions that change data.

The catalog lists the fields and capabilities available in the supplied provider definition. Availability can also depend on your deployment and organization’s Feature Access settings.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/integrations/catalog/cartesia.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
