---
canonical_url: "https://docs.composio.dev/toolkits/cartesia"
markdown_url: "https://docs.composio.dev/toolkits/cartesia.md"
product: "platform"
version: null
last_updated: null
---

# Cartesia

Cartesia provides real-time text-to-speech, speech-to-text, voice, model training, and managed voice agent APIs.

- **Category:** artificial intelligence
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 10
- **Triggers:** 0
- **Slug:** `CARTESIA`
- **Version:** 00000000_00

## Tools

### Create Pronunciation Dictionary

**Slug:** `CARTESIA_CREATE_PRONUNCIATION_DICTIONARY`

Create a reusable pronunciation dictionary for text-to-speech generation.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | Yes | Name for the pronunciation dictionary. |
| `items` | array | No | Initial text-to-pronunciation mappings for the dictionary. |
| `access` | string ("private" | "public") | No | Who may use the dictionary: private restricts it to the owning organization; public allows any Cartesia user with its ID. |
| `description` | string | No | Optional description of the dictionary's purpose. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Pronunciation Dictionary

**Slug:** `CARTESIA_DELETE_PRONUNCIATION_DICTIONARY`

Permanently delete one pronunciation dictionary by ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `dictionary_id` | string | Yes | ID of the pronunciation dictionary to permanently delete. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Pronunciation Dictionary

**Slug:** `CARTESIA_GET_PRONUNCIATION_DICTIONARY`

Return one pronunciation dictionary and its complete text-to-pronunciation mappings.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `dictionary_id` | string | Yes | ID of the pronunciation dictionary to retrieve. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Voice

**Slug:** `CARTESIA_GET_VOICE`

Return synthesis-relevant details for one Cartesia voice by ID.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | ID of the voice to retrieve; obtainable from List Voices. |
| `include_preview_url` | boolean | No | Include the voice's preview audio URL when true. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Accents

**Slug:** `CARTESIA_LIST_ACCENTS`

List supported accents, optionally filtered by language, locale, or voice-localization support.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `locale` | string | No | Filter by locale code, such as en-US or es-MX. |
| `language` | string | No | Filter by language code, such as en or es. |
| `localizable_only` | boolean | No | When true, return only accents available for voice localization. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Agent Models

**Slug:** `CARTESIA_LIST_AGENT_MODELS`

List language models available to Cartesia Managed Agents, including provider, latency, and pricing metadata.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum models to return in this page (1-100). |
| `cursor` | string | No | Continuation cursor returned by a previous call. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Pronunciation Dictionaries

**Slug:** `CARTESIA_LIST_PRONUNCIATION_DICTIONARIES`

Return one page of pronunciation dictionaries available to the connected account.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum dictionaries to return in this page (1-100). |
| `cursor` | string | No | Continuation cursor returned by a previous call. Omit for the first page. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Voices

**Slug:** `CARTESIA_LIST_VOICES`

Search and filter Cartesia voices, returning one page of voice IDs and synthesis-relevant metadata.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum voices to return in this page (1-100). |
| `cursor` | string | No | Continuation cursor returned by a previous call. Omit for the first page. |
| `gender` | string ("masculine" | "feminine" | "gender_neutral") | No | Filter by voice gender presentation. |
| `language` | string | No | Filter by language or locale code, such as en or en-GB. |
| `owned_only` | boolean | No | When true, return only voices owned by the connected organization. |
| `search_query` | string | No | Search voice names, descriptions, or IDs. |
| `include_archived` | boolean | No | Include archived voices when true. |
| `include_preview_url` | boolean | No | Include each voice's preview audio URL when true. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Synthesize Speech

**Slug:** `CARTESIA_SYNTHESIZE_SPEECH`

Generate a downloadable audio file from one complete transcript using a selected Cartesia voice; usage is billed by transcript length.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `speed` | number | No | Optional generation speed setting for sonic-3 and newer. |
| `accent` | string | No | Optional accent ID supported by the selected voice; normally omit to let Cartesia choose. |
| `volume` | number | No | Optional generation volume setting for sonic-3 and newer. |
| `emotion` | string ("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") | No | Optional primary emotion to guide speech generation on sonic-3 and newer. |
| `encoding` | string ("pcm_f32le" | "pcm_s16le" | "pcm_mulaw" | "pcm_alaw") | No | Audio encoding valid for the selected output container. |
| `language` | string | No | Transcript language or locale code, such as en or en-GB. |
| `model_id` | string ("sonic-3.6" | "sonic-3.5" | "sonic-3" | "sonic-latest") | No | Cartesia speech model to use. |
| `voice_id` | string | Yes | Voice ID from List Voices. |
| `transcript` | string | Yes | Complete text to synthesize; usage is billed by transcript length. |
| `sample_rate` | integer ("8000" | "16000" | "22050" | "24000" | "44100" | "48000") | No | Output sample rate in hertz; must be valid for the selected container and encoding. |
| `normalization` | string | No | Use auto, off, or a language/locale code to control text normalization. |
| `output_container` | string ("wav" | "mp3" | "raw") | No | Audio file/container format. |
| `pronunciation_dictionary_id` | string | No | Optional pronunciation dictionary ID to apply; supported by sonic-3 and newer. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Update Pronunciation Dictionary

**Slug:** `CARTESIA_UPDATE_PRONUNCIATION_DICTIONARY`

Update a pronunciation dictionary and replace its mappings with the complete supplied item set.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `name` | string | No | New dictionary name; omit to leave the name unchanged. |
| `items` | array | Yes | Complete intended mapping set. This replaces the dictionary's existing mappings, so include every mapping that should remain; an empty list clears all mappings. |
| `access` | string ("private" | "public") | No | New access level; omit to leave it unchanged. |
| `description` | string | No | New dictionary description; omit to leave it unchanged. |
| `dictionary_id` | string | Yes | ID of the pronunciation dictionary to update. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |