Is there a way to get your own custom voices for text to speech

I am working on a project and was wondering if I could have different voices for text to speech instead of the basic creepy robot one.

This api MIGHT work for App Inventor. If you try it let us know if it works. :thinking:

Yes, there is a way to explore custom voices for Text-to-Speech (TTS), although it might require stepping a bit outside the standard App Inventor components.

Right now, the built-in TTS in App Inventor generally uses the device's default engine typically Google Text-to-Speech on Android, which has a limited set of voices. But if you're looking for custom or more human-like voices, here are a few creative ways you can try:

  1. Install a Different TTS Engine

You can install third-party TTS engines like Vocalizer TTS, Acapela, or MyVoice from the Play Store. Once installed, you can set one of these as the default engine in your device's accessibility settings. App Inventor’s TTS component will then use this engine automatically.

  1. Cloud-Based APIs

If you want studio-quality voices or character-specific tones, consider using cloud services like:

  • Google Cloud Text-to-Speech
  • Amazon Polly
  • IBM Watson TTS

Offline Engine: Some engines like eSpeak or RHVoice allow offline support and even support creating your own voice models, though this requires more advanced setup.

@SquareRootSolutionUK
Nice chatgpt/generatiove ai response

how would i use a software such as eSpeak with my project

my school doest allow google cloud services

Use eSpeak as Your Default TTS Engine (on Android)

  • Install eSpeak TTS from the Google Play Store
  • Settings > Accessibility > Text-to-Speech Output
  • default TTS engine to eSpeak TTS
  • Go back to your App the Text-to-Speech component will now use eSpeak

you can also use eSpeak NG or an eSpeak-compatible Android app

Hey!

I appreciate your comment, but just to clarify, this response wasn’t generated by ChatGPT or any AI tool. I’ve been actively working with tools like App Inventor and exploring TTS options like eSpeak firsthand, so I simply wanted to share what’s worked for me and what I’ve learned along the way.