# How to use local Whisper instance in BoltAI

The Whisper model is a speech to text model from OpenAI that you can use to transcribe audio files. In BoltAI, you can use the Whisper model via OpenAI API, Groq or a custom server.

Follow this step-by-step guide to setup and use a local Whisper instance in BoltAI

### 0. Prerequisites

Make sure your local Whisper instance is up and running. This is outside the scope of this guide. Here are some pointers for you:

* [tiny-openai-whisper-api](https://github.com/morioka/tiny-openai-whisper-api)
* [whisper.cpp](https://github.com/ggerganov/whisper.cpp)
* [lightning-whisper-mlx](https://github.com/mustafaaljadery/lightning-whisper-mlx)
* [whisper-turbo-mlx](https://github.com/JosefAlbers/whisper-turbo-mlx)
* [openedai-whisper](https://github.com/matatonic/openedai-whisper)

### 1. Add a custom service in BoltAI

* Go to Settings > Models. Click the plus (+) button and select "OpenAI-compatible Server"
* Fill the form, make sure to enter the **full URL** to the API endpoint
* Click **"Save (Skip Verification)"**

<figure><img src="/files/XPDs1gFQUIr0nvOI6ddb" alt=""><figcaption><p>Setup a custom service in BoltAI</p></figcaption></figure>

### 2. Configure BoltAI to use this custom service

* Go to Settings > Advanced > Voice Settings
* In the "Whisper Settings" section, select your newly created service ("Local Whisper" in this example)

Now both the main chat UI and the Inline Whisper will use this local whisper instance instead of OpenAI.

<figure><img src="/files/YDiF6jD8UgOS5OHtBKmd" alt=""><figcaption><p>Configure BoltAI to use the local Whisper instance</p></figcaption></figure>

### That's it

It's pretty simple, isn't it? If you have any question, feel free to send me an email. I'm happy to help.


---

# 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.boltai.com/blog/how-to-use-local-whisper-instance-in-boltai.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.