Text-To-Speech Support

As a Roblox developer, it is currently too hard to turn text into audio. I’m working on an experience where users create funny content and share it, similar to a lot of social media apps. Our problem is that apart from sound effects we upload ourselves, we have no voices. Pre-recorded messages get old and almost never say exactly what the user wants.

If Roblox were to fix this issue it would massively help us improve engagement for our UGC content. We could use Roblox’s translation service to translate the base text into whatever we’d like, then use Roblox Text-To-Speech to vocalize the text. This would be great for memes, how-tos, commentaries, or any sort of video-type content where narration is beneficial.


Just adding on to this.

What would be even better is if this could be integrated into facial animations, so we could make characters and avatars actually talk with a voice.


Big support.

As someone who frequently uses voice chat, but has to rely on outside workarounds (virtual cable connected to TSS software which is connected to roblox)
in order to be heard.

It would be pretty nice if roblox actually implemented it into avatars, thus allowing people with certain disabilities (or those who are not comfortable with their voice like me) to actually be heard with some sort of voice instead of just a floating chat bubble that lacks any possible customization/personalization properties depending on a player.

It also would be nice if roblox would let us make a custom TTS voice based on sliders for our avatars (something similiar to what nintendo did for miis in several games) and then make it so your avatar actually says out loud whatever you have said in the text chat.


As much as I feel like text-to-speech should be implemented, I do not feel that it should be implemented into voice chat, generally speaking developers could implement this themselves if a text-to-speech api was added. And having text-to-speech as a default feature would reduce immersion in certain types of experiences, for example, horror games.

As for your point of ‘not revealing your voice yet’, I do not see why you would need text-to-speech to acheive this goal, not only is text to speech a bit annoying for some users when used a lot, but there is no reason why you can’t use the text-chat to fufill this goal and have players read your messages instead.

As for the lack of customisation when using text-chat, I feel like this is a seperate issue that should be adressed by the developers of the experience rather than Roblox, many customisation options simply don’t fit the vision of an experience.


As someone looking into using Roblox for educational purposes (pre-K), this is pretty much the last step needed for a reading-typing teaching project of mine. With official text-to-speech support, I’d be able to quickly make soundbytes for just about any word out there instead of having to record and upload them myself tediously.


Sorry for bumping this topic. But you can make a custom text-to-speech system by making or downloading sounds that are from the alphabet. You could try adding custom facial animations as well. If Roblox WERE to implement this, I would see no use really.


If Roblox were to implement this, the use would be having text-to-speech without every developer having to upload 44 different sounds (per voice) and script a system for it. I can’t imagine splicing sounds like that would sound nearly as good either, since text-to-speech algorithms are much more complicated than that.


PLEASE ADD THIS OMG because of the audio limit it is so hard to make characters talk.

Upload 7-minute-long segments of dialog into one audio. Roblox will release a feature soon allowing you to play certain segments of audio at a time.

Trust me, I read the documentation.

This would be really useful for games with a lot of dialog. You could use that for that

It would be easier still to just have a command like


If they actually made that command I am pretty sure everyone will be happy.

1 Like

One simple way for roblox to implement this both client side and server side is using Mimic 3 by Mycron AI. Its a open source TTS implementation, with hundreds of voices in a lot of languages, most of them sounding very realistic, with a simple web API. Roblox just has to integrate it into the player client, and create a simple wrapper for the http api. Something like this would be nice:

local audioResult = tts("Text to be spoken", {
      "voice": "en_US/cmu-arctic_low",  // voice key
      "speaker": "fem",  // default speaker
      "length_scale": 1.0,  // speaking rate
      "noise_scale": 0.667,  // speaking variablility
      "noise_w": 1.0  // phoneme duration variablility

It should return some id (For example rbxttsaudio://12345678) That will be disposed in a few minutes, so we can use it in actual audio objects.


Pronunciation goes brrrrrrrrrrr

1 Like

Can you give a script to Implement this using http api?

There’s no way to implement this in roblox, since there will be no way to actually play the sound (you cannot upload audios in real time, and there is a big delay for uploading audios, which is why I want this to be a roblox feature)

Bump, I would love this being added, like there are so many things developers could do with this, for instance, when a player wins the game say it in text to speech.

Player.Name.." won the game with"..points.." amount of points"

Someone at ROBLOX made a prototype during hack week of 2018, this needs to be added please.


Also bumping this, if roblox is looking towards accessibility then they have to finally consider t2s, it’s way too complicated and low-quality when it’s a custom system due to the limit of audio uploading and the time it takes for it to be moderated + lua is slow as hell. We have voice chat so why not this? Especially since there’s “AI” generated voices nowadays and Roblox is investing in this subject :person_shrugging: I can imagine that practically all games would benefit from this or use it lol

Support. Would be useful for accessibility as well as games with captioning or cutscenes.

I see this probably better than uploading audio assets, since it would save my quota from being used.

One drawback, moderation, some developers could take advantage of this and use it to break the roblox ToS (profanity, and saying to visit certain inappropriate sites), so there would have to be some sort of restriction on what can be said, so for example, to replace or refuse to play the audio.