SAMMI Text to Speech
If Ko-Fi is your preferred platform, feel free to access the download through this link: Ko-Fi Link
This 3-in-1 extension for SAMMI is all you need for your Text-To-Speech needs!
It supports regular Web Speech API, Google API and Amazon Polly API for text synthesis. That's around 400 different voices and over 50 languages!
Web Speech API
Web Speech API is a completely free and unlimited API for TTS. It contains all voices supported by your Windows and works when running Bridge from within OBS in a dock (only for OBS 27.2 and higher).
Google Cloud Text-to-Speech
Google provides its own TTS service with around 300 voices and 50 languages.
Google Cloud's free tier lets you use up to 4 million standard or 1 million neural characters per month for completely free. The free usage limit does not expire, but may be subject to change.
See the up-to-date pricing details at the official Google site.
Google TTS requires a valid credit card to confirm your identity.
Amazon Polly
Amazon provides a TTS service with around 66 different voices.
You get a free tier for the first 12 months starting from your first request for speech.
The free tier includes 5 million standard and 1 million free neural characters per month.
See the up-to-date pricing details at the official AWS site.
Amazon TTS requires a valid credit card to confirm your identity.
Playback Controls
You can play, pause, skip and control the volume of your TTS (some commands are not fully supported for the regular Web Speech API).
Voice Settings
You can change the pitch and speed for all TTS services.
Amazon Polly offers soft and whispered voices.
Random Voice
For each service, you can choose the TTS voice to be completely random! That will make for some funny moments for your viewers for sure!
Automatic Queue
You can easily queue up all your TTS requests and they will be played one by one. This is fully automatic!
Queue for Polly and Amazon TTS is combined, while Web Speech API has its own separate queue.
SSML Support
Google and Polly TTS voices support custom SSML queries.
Interested in custom modifications for this extension? I offer commissioned work to adapt and personalize my extensions to your unique needs. For more information, reach out to me on Discord (christinna).
Special thanks goes to:
All my amazing Patrons!
If you would like to support me in creating more extensions for SAMMI, you can become my Patron to get early free access to my extensions or make a Paypal donation.
DISCLAIMER: The extension is provided as is. The developer has no obligation to provide maintenance and support services or handle any bug reports.
Feel free to edit the extension for your own use. You may not distribute, sell or publish it without the author’s permission.
Purchase
In order to download this project you must purchase it at or above the minimum price of $4.99 USD. You will get access to the following files:
Development log
- Web TTS Google Voices Are Broken19 days ago
- Text To Speech 1.5 Update98 days ago
- Text To Speech 1.4 UpdateApr 01, 2024
- Update to support SSMLMar 02, 2023
- Web TTS Commands Not Loading FixFeb 17, 2023
- Bug Fix for Random VoicesSep 10, 2022
Comments
Log in with itch.io to leave a comment.
VERY HIGHLY recommend this, I've been using it to give TTS to my moderators on streams (with their own voices and talking avatars that pop up!) and for a "60 seconds of TTS" redemption. It works REALLY well and is compatible with a lot of coding trickery to make it work however you want!
Pro Tip: Open the TTS browser source in Edge because that browser has a TON of free voices to choose from built into it!
Hey, thanks so much for your review and comment! Great tip with the Edge browser, too :)
Hello! Is there a way to check If TTS is over?
Hello, there’s a speaking variable that you can check if it’s true (=speaking) or false (=not speaking).
Hi. Does this extension allow you to read out twitch sub messages?
Hey there. Yes it does. It’s just a simple SAMMI trigger and one command to pull the sub message to send it to the TTS. Super simple to add!
heya! im assuming its not possible to play multiple web TTS at the same time, they can only be queued?
Hi, that’s correct. It would need some custom modifications to be able to do that. Please reach out to me on Discord if you’re interested in that!
This looks great! I've been fiddling around with it, but is there any way to change the audio source it comes in through?
Hey there, the audio comes from your docked Bridge, but you could run Bridge in a browser outside of OBS instead, too, and then the audio would come directly from your browser. I’m planning on releasing an updated version though, where you’re going to be able to change the audio source more easily.
Awesome! Thank you for the suggestion!
is there a proper setup guide for this? I can't figure it out.
Hi, yes there is! Here’s the link: https://sammi.solutions/extensions/audio/tts-k#pills-setup :) If you need further assistance, you can always join our SAMMI Discord at https://discord.gg/dXez8Zh and ask in the Extension support channel.
Thanks for your help in discord!