> 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/murf-ai.md).

# Murf AI

Generate speech, browse voices, translate text, and convert audio with Murf AI.

### Connectors

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

| Connector | Authentication |
| --------- | -------------- |
| Murf AI   | API Key        |

#### Murf AI

Connect to Murf AI to generate speech, browse voices, translate text, and convert audio with an API key.

**Set up in Murf AI**

1. Prepare the Murf AI account or service that the workflow will access. Grant access to the required resources and operations.
2. **API Key:** Create an API key in the Murf API Dashboard.

**Set up in StackAI**

1. Open **Settings → Connections**, add a connection, and select **Murf AI**.
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      | Create an API key in the Murf API Dashboard. [Provider instructions](https://murf.ai/api/docs/introduction/quickstart). |

#### 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 **Murf AI** 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 from Text

Turn text into spoken audio with a Murf voice.

**Inputs**

| Field               | Type            | Required | Description                                                                                                |
| ------------------- | --------------- | -------- | ---------------------------------------------------------------------------------------------------------- |
| Text                | textarea        | Yes      | The text Murf should speak, up to 3,000 characters.                                                        |
| Voice               | select (string) | Yes      | The Murf voice that will speak the text. Options load from the selected connection.                        |
| Language and Locale | select (string) | No       | The language and regional pronunciation for the selected voice. Options load from the selected connection. |
| Speaking Style      | select (string) | No       | An optional delivery style supported by this voice and locale. Options load from the selected connection.  |
| Audio Format        | select (string) | No       | The format of the generated audio. Available values: MP3, WAV, FLAC, ALAW, ULAW, PCM, OGG. Default: MP3.   |
| Zero Retention      | boolean         | No       | Return Base64 audio instead of storing an audio link on Murf for 72 hours. Default: false.                 |

**Outputs**

| Field                   | Type    | Description                                          |
| ----------------------- | ------- | ---------------------------------------------------- |
| Audio URL               | string  | The generated audio link when zero retention is off. |
| Encoded Audio           | string  | Base64-encoded audio when zero retention is on.      |
| Audio Length in Seconds | number  | The duration of the generated audio.                 |
| Remaining Characters    | integer | Characters remaining in the current Murf allowance.  |
| Warning                 | string  | Any warning returned with the generated audio.       |

#### List Voices

Browse Murf voices and their supported locales and styles.

**Inputs**

| Field | Type            | Required | Description                                                                           |
| ----- | --------------- | -------- | ------------------------------------------------------------------------------------- |
| Model | select (string) | No       | Filter voices by Murf speech model. Available values: Gen 2, Falcon 2. Default: gen2. |

**Outputs**

| Field       | Type          | Description                                                            |
| ----------- | ------------- | ---------------------------------------------------------------------- |
| Voices      | object\_array | Structured voice records with identifiers, names, locales, and styles. |
| Voice Count | integer       | The number of voices returned.                                         |

#### Translate Text

Translate text into a supported language with automatic source detection.

**Inputs**

| Field           | Type            | Required | Description                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
| --------------- | --------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Text            | textarea        | Yes      | The text to translate, up to 4,000 characters. Maximum: 4000.                                                                                                                                                                                                                                                                                                                                                                                                                |
| Target Language | select (string) | Yes      | The language and locale for the translated text. Available values: English - US & Canada, English - UK, English - India, English - Australia, English - Scotland, Spanish - Mexico, Spanish - Spain, French - France, German - Germany, Italian - Italy, Dutch - Netherlands, Portuguese - Brazil, Mandarin - China, Japanese - Japan, Korean - Korea, Hindi - India, Tamil - India, Bangla - India, Croatian - Croatia, Slovak - Slovakia, Polish - Poland, Greek - Greece. |

**Outputs**

| Field           | Type   | Description                                       |
| --------------- | ------ | ------------------------------------------------- |
| Source Text     | string | The original text returned by Murf.               |
| Translated Text | string | The translated text.                              |
| Target Language | string | The target language code used by Murf.            |
| Credits Used    | number | The translation credits consumed by this request. |

#### Convert Voice of Audio File

Transform a reachable audio file into a selected Murf voice.

**Inputs**

| Field        | Type            | Required | Description                                                                                            |
| ------------ | --------------- | -------- | ------------------------------------------------------------------------------------------------------ |
| Audio URL    | string          | Yes      | A publicly reachable URL for the source audio file.                                                    |
| Voice        | select (string) | Yes      | The Murf voice to apply to the recording. Options load from the selected connection.                   |
| Audio Format | select (string) | No       | The output format for the converted audio. Available values: MP3, WAV, FLAC, ALAW, ULAW. Default: MP3. |

**Outputs**

| Field                   | Type    | Description                                                    |
| ----------------------- | ------- | -------------------------------------------------------------- |
| Audio URL               | string  | The converted audio link, retained by Murf for about 24 hours. |
| Audio Length in Seconds | number  | The duration of the converted audio.                           |
| Remaining Characters    | integer | Characters remaining in the current Murf allowance.            |
| Warning                 | string  | Any warning returned with the conversion.                      |

#### Generate Speech with Word Timestamps

Generate spoken audio with word-level timing for captions or highlighting.

**Inputs**

| Field                            | Type            | Required | Description                                                                                                      |
| -------------------------------- | --------------- | -------- | ---------------------------------------------------------------------------------------------------------------- |
| Text                             | textarea        | Yes      | The text Murf should speak and time, up to 3,000 characters.                                                     |
| Voice                            | select (string) | Yes      | The Murf voice that will speak the text. Options load from the selected connection.                              |
| Language and Locale              | select (string) | No       | The language and regional pronunciation for the selected voice. Options load from the selected connection.       |
| Speaking Style                   | select (string) | No       | An optional delivery style supported by this voice and locale. Options load from the selected connection.        |
| Audio Format                     | select (string) | No       | The format of the generated audio. Available values: MP3, WAV, FLAC, ALAW, ULAW, PCM, OGG. Default: MP3.         |
| Use Original Text for Timestamps | boolean         | No       | For English text, align timestamp words to the original input instead of normalized speech text. Default: false. |
| Zero Retention                   | boolean         | No       | Return Base64 audio instead of storing an audio link on Murf for 72 hours. Default: false.                       |

**Outputs**

| Field                   | Type          | Description                                                |
| ----------------------- | ------------- | ---------------------------------------------------------- |
| Audio URL               | string        | The generated audio link when zero retention is off.       |
| Encoded Audio           | string        | Base64-encoded audio when zero retention is on.            |
| Audio Length in Seconds | number        | The duration of the generated audio.                       |
| Word Durations          | object\_array | Structured words with start and end times in milliseconds. |
| Remaining Characters    | integer       | Characters remaining in the current Murf allowance.        |

### 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/murf-ai.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.
