# Speech To Text

### Speech To Text From Sound Wave

* **Description:** Transcribes the provided audio.

<figure><img src="https://413558230-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEtUJA212Zc1S9ACc8T4l%2Fuploads%2FCAQoqjis2PdGTMWwun5t%2Fimage.png?alt=media&#x26;token=ddbe14b7-212e-4e83-a569-9f0ede5f1460" alt=""><figcaption></figcaption></figure>

**Inputs:**

* **Sound Wave:** The recorded output from the microphone, please take a look over the tutorial/sample project for an example on how to use Convai voice capture component with the API.

**Outputs:**

#### ✅ \[On Success]

**Response:** Contains the text output of the audio file if the API was successful, otherwise might contain information on why the API call failed.

#### ⛔ \[On Failure]&#x20;

*Nothing is returned, check logs for details on why it failed.*

### Speech To Text From Sound Wave

* **Description:** Transcribes the provided audio file.

<figure><img src="https://413558230-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FEtUJA212Zc1S9ACc8T4l%2Fuploads%2FhzaOsP7s8iM2pafmE72r%2Fimage.png?alt=media&#x26;token=1ef2f748-3e3a-48e8-b3c2-a23797b20f57" alt=""><figcaption></figcaption></figure>

**Inputs:**

* **Filename:** The path to the recorded audio file on your local disk, the file should be in a .wav format.

**Outputs:**

#### ✅ \[On Success]

**Response:** Contains the text output of the audio file if the API was successful, otherwise might contain information on why the API call failed.

#### ⛔ \[On Failure]&#x20;

*Nothing is returned, check logs for details on why it failed.*


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/unreal-engine/blueprints-reference/speech-to-text.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.