> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/workflows/workflow-inputs/upload-audio.md).

# Upload Audio

The **Upload Audio** control is an input component that allows a user to upload an audio file (e.g., MP3, WAV, M4A) when they run a workflow. The uploaded audio is then accessible via a temporary URL that can be used by downstream nodes for processing.

## When to Use

Use the Upload Audio control for any workflow that needs to process a user-provided audio file. Common use cases include:

* Transcribing speech to text.
* Summarizing the content of a meeting or call.
* Translating speech from one language to another.
* Identifying different speakers in a recording.

## How to Add

1. From your workflow's **Build** page, click on **+ Add Input**.
2. Select **Upload Audio** from the list of available controls.

## Configuration

* **Title:** The main label for the file upload field.
* **Description:** Optional helper text to provide more context.
* **Variable Name:** The name used to access the URL of the uploaded audio file.
* **Optional/Required:** A toggle to specify if the user must upload a file.

## Accessing the Value

After the user uploads a file, this control outputs a temporary, secure URL pointing to that audio file. This URL is accessible via the variable name you assigned.

For example, if the variable name is `podcast_episode`, the value of `{{podcast_episode}}` will be a URL (e.g., `https://cdn.agenticflow.ai/.../episode.mp3`).

**Note:** This URL is temporary and will expire. It is meant for immediate processing within the workflow run.

### Example

**Goal:** Allow a user to upload a recording of a customer support call and generate a summary and a list of action items.

1. **Add an Upload Audio Control:**
   * Title: "Upload Support Call Recording"
   * Variable Name: `call_recording_url`
2. **Add an OpenAI MCP Node (Whisper):**
   * **Action:** `Create Transcription`
   * **File:** `{{call_recording_url}}`
   * **Purpose:** To convert the spoken audio into text.
3. **Add another OpenAI MCP Node (GPT):**

   * **Action:** `Chat`
   * **Prompt:**

   ```
   Read the following transcript of a customer support call. Provide a one-paragraph summary of the issue and a bulleted list of action items for the support agent.

   Transcript:
   {{openai_mcp_1.text}}
   ```

   * **Purpose:** To analyze the transcribed text and extract key information.

This workflow takes a raw audio file and turns it into a structured, actionable summary, automating the post-call analysis process.


---

# 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 dynamically by asking a question.

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

```
GET https://docs.agenticflow.ai/workflows/workflow-inputs/upload-audio.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.