# Voice input, face-to-face translation and Voice Studio

NanoMouse offers speech-to-text and cleanup, two-way conversation translation, and text-to-speech creation with voice selection and multi-speaker dialogue.

Voice input starts from the keyboard and uses the main app for recording and recognition. Review the transcript and optionally clean up filler words, punctuation and structure. Apple, local and online recognition options depend on settings, device and language.

Face-to-face translation combines recognition, translation and read-aloud for two people speaking different languages. It requires a supported OS, microphone permission and the selected services. Results should be checked when accuracy matters.

Voice Studio turns text into audio, with voice selection, performance settings, multi-speaker dialogue, saving and sharing. Recognition, text cleanup and synthesis are separate processing steps and online services use the applicable account allowance.

## How to use it

1. Open the voice tool and configure required permissions.
2. Choose a recognition language or both conversation languages.
3. Review the result; save or share generated audio from Voice Studio.

## Why does voice input open the main app?

The main app handles microphone recording and recognition before returning text to the input workflow.

## How does Voice Studio differ from dictation?

Dictation converts speech into text; Voice Studio converts text into audio. Conversation translation combines recognition, translation and read-aloud.

Verified November 6, 2026. The public App Store version is 3.4.7; cloud membership services have been updated. Client-only 3.4.8 capabilities are not presented as already released. Features and interfaces vary by device, OS, region and version.

Source: https://nanomouse.top/features/voice/