Merge branch '3225-murena-voice-to-text' into 'master'

## Overview

The Murena Voice to Text feature in /e/OS allows you to dictate text instead of manually typing it. This feature is exclusively available to Murena Workspace Premium users. By using this feature, you can easily convert your spoken words into written text, making it convenient for composing messages, emails, notes, and more.

## Prerequisites

- An /e/OS device.

- A Murena Workspace Premium subscription. [Subscribe here](https://murena.com/cloud-subscriptions/).

## Enabling the Voice to Text Feature

1. **Connect Your Account:** Ensure your Murena Workspace account is connected on your /e/OS device through the Account Manager

2. **Subscribe to a Premium Plan:** If you haven't already, subscribe to a Murena Workspace Premium plan to access the Voice to Text feature.

## Using the Voice to Text Feature

1. **Access the Keyboard:** Open any application where you need to input text (e.g., Message, Mail, Notes).

2. **Activate Voice to Text:** Tap the microphone icon on the keyboard to start dictating.

3. **Dictate Your Text:** Speak clearly into the microphone. Your spoken words will be converted to text in real-time.

4. **Deactivate Voice to Text:** Tap the microphone icon again to stop dictating and return to the regular keyboard.

## Tips for Optimal Use

- **Speak Clearly:** Enunciate your words clearly for better accuracy.

- **Minimize Background Noise:** Use the feature in a quiet environment to improve recognition accuracy.

## Troubleshooting

- **Feature Not Available:** Make sure:

   - you have a Murena Workspace Premium subscription.

   - your Premium account is connected on your device through the Account Manager.

   - your device has internet access

If you match these conditions but still don't have access to the feature, reboot your phone.

## Privacy and Security

The Voice to Text feature uses the OpenAI Realtime Transcription API, specifically configured to use the `gpt-4o-mini-transcribe` model. This model is chosen as it supports real-time transcription, which is not available with the `whisper-1` model. This ensures high accuracy and efficiency in converting speech to text. More information about the OpenAI Realtime transcription API available at [https://platform.openai.com/docs/guides/realtime-transcription](https://platform.openai.com/docs/guides/realtime-transcription).

To enhance privacy and security, the Murena Voice to Text keyboard employs a proxy to anonymize requests made to the OpenAI API. This set-up ensures that your data remains secure and your privacy is protected. This is also explained in our [Terms and Conditions](https://murena.io/en/termsandconditions).

For transparency and further assurance, the source code for the Murena Voice to Text keyboard is available at [https://gitlab.e.foundation/e/os/murena-voice-to-text](https://gitlab.e.foundation/e/os/murena-voice-to-text). Additionally, the source code for the proxy is available at [https://gitlab.e.foundation/e/infra/proxy-stt](https://gitlab.e.foundation/e/infra/proxy-stt).

---

layout: page

title: Murena Voice to Text

permalink: /murena-voice-to-text

toc: true

---

{% tf pages/murena-voice-to-text.md %}

 No newline at end of file