> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chariot.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Microphone demo

> Try streaming speech to text with your microphone and API key, without writing code.

Get an API key from the [dashboard](https://platform.chariot.in), paste it below, and select **Start recording**. Allow microphone access and speak. Select **Stop and transcribe** to receive the final transcript.

### Try it with your microphone

Paste your API key, start recording, and speak. Your transcript appears here.

API key

Mode

Auto-finalize after pauses

Live transcript

Uses your workspace credits. The demo stops after two minutes. Your key stays in this page's memory and is sent only to the Chariot API. Closing this page stops recording.

**Auto-finalize after pauses** confirms each utterance after 500 milliseconds of silence and keeps listening. Turn it off to receive one final transcript when you stop. Choose **Balanced** for faster feedback or **High accuracy** for more context. Language detection is automatic.

The demo uses the same [ASR WebSocket API](https://docs.chariot.in/api-reference/endpoint/asr-websocket.md) as your application and charges your workspace's normal speech-to-text credits. The two-minute recording cap applies to this demo, not the API.

> [!NOTE]
>
> Closing or reloading the page stops the recording and clears the transcript and API key from the demo. Copy any text you want to keep before leaving. For application integration, keep your API key on your server.

## Inspect the API messages

The [WebSocket reference](https://docs.chariot.in/api-reference/endpoint/asr-websocket.md) also has a developer playground. Enter your API key under **Security Schemes**, select **Connect**, and wait for `session.started`.

* **Keep alive** resets the idle timer. It has no response.
* **Commit a segment** finalizes audio sent so far and keeps the session open.
* **End input** returns the remaining transcript and closes the connection.

These control messages are prefilled. To send microphone audio, use the demo above. See the [streaming guide](https://docs.chariot.in/guides/speech-to-text/websocket.md) for the full protocol and [quickstart](https://docs.chariot.in/guides/speech-to-text/quickstart.md) for runnable client code.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.