Skip to main content

Speech Mode on Android

This page covers the Android setup for Speech Mode. For how it works and use cases, see the Speech Mode overview.

How to Use Speech Mode on Android​

  1. Open the Whisperr app
The Whisperr app open on Android showing the New Conversation screen
  1. Select your source language (what you'll be hearing) and target language (what you want spoken back)
Selecting the input language on Android
  1. Open the ••• options menu in the recording bar to find the Speech settings:
    • Enable Real-Time Speech — speaks each translated line aloud as soon as it's confirmed
    • Show Speech Button — adds a speaker icon next to each transcription and translation so you can replay any line on demand
    • Voice — Auto, Male, or Female (see below)
    • Speaking Speed — adjust the playback rate from 0.5× to 2×
Speech settings on Android with Enable Real-Time Speech turned on
  1. Tap the microphone to start — with Real-Time Speech on, Whisperr reads each translated line aloud as it appears
Live transcription and translation on Android with Speech Mode on
  1. Optionally connect headphones for private listening — or, if you're using the loudspeaker, leave Echo Cancellation on in Settings (it is on by default) so the spoken translation isn't picked back up by the mic and translated again. See Echo Cancellation on iPhone & Android.

Toggle Enable Real-Time Speech off to silence the spoken audio while keeping the on-screen translation running. Your speech settings are remembered for next time.

Choosing the Voice​

The Voice picker sits next to the speech controls — in the speech panel of the recording bar, and again under Settings, so you can set it before a recording as well as during one:

  • Auto (default) — Whisperr reads translations in the standard voice for your target language
  • Male / Female — every line is read in a fixed male or female voice instead, whoever is speaking

Change the voice mid-recording and it applies from the next spoken line; your choice is remembered for next time.

Matching the voice to each individual speaker is available in the Web App — see Choosing the Voice in the overview, and Voice Support by Language for what each language supports.