Dear AppleVis community,
AccessMind is proud to announce the first public beta of Runa TTS, a new text-to-speech engine for iOS that brings high quality, natural sounding, neural voices from ReadSpeaker, a global pioneer in the field of human-like TTS technology, to be used with VoiceOver, as well as other applications that use Apple's speech synthesis APIs.
Enjoy classics such as Paul, Kate and Julie from the Neo speech days, or new voices in 50 languages, including English, Arabic, Hebrew, French, German, Spanish, and many others.
The application also includes some advanced features, such as:
- Voice Profiles, allowing you to configure various settings such as speech rate, pitch, and maximum volume per-voice, and forcing them even if VoiceOver is set to different values.
- Automatic language switching based on Unicode characters for Arabic, Latin, Hebrew, Russian, and Greek even if VoiceOver does not support it in your language or region, configured on a per-voice profile level.
- iCloud sync between devices to make sure all voice profiles and voice settings stay up to date between devices.
- In a future update, Siri shortcuts will be introduced for switching voice profiles on the fly.
Once you download and install the application, focus will land on the βmanage voicesβ tab, allowing you to download voices and filter them by language, quality, etc. 2 qualities are available for each voice: standard and enhanced. We strongly recommend using the enhanced quality.
Every voice will be a switch button, when checked, it will be added to the queue, and a button to install all selected voices will appear at the bottom of the screen, before the tab bar. Activating this button will install all selected voices. If voices are installed, checking them will cause a button to remove all selected voices to appear instead.
Once installed, you can add the voices to Voiceover using the VoiceOver speech settings, including configuring them as primary, and adding them to the rotor.
The settings tab, contains all the advanced features, such as Voice profiles, and iCloud syncing. Both are disabled by default, to avoid confusion.
Important notes
- Due to bugs with iOS 27, language switching by Unicode characters will not work properly if configured through our engine, it will only work through VoiceOver with the way Apple has chosen to implement it. We will communicate with Apple to hopefully get this fixed.
- There are no bundled voices with the app. You have to download the voices you wish to use from the manage voices tab.
Feedback during the public beta
Please send all your questions, comments, and queries, to: adi@accessmind.net
Pricing
Pricing for the final product, including subscription or perpetual licensing models, has not been decided yet. The public beta will be available to try for free at least until September.
Installing the public beta
Please use the following TestFlight link to install the public beta of Runa TTS on your devices:
https://testflight.apple.com/join/bJQ5UpWQ
We look forward to hearing from you!
Comments
It doesn't seem to work on iOS16 at all.
It seems that on my iPhone running ios16.5.1, no matter what kind of voice I choose, it can only use the default voice in the end. I thought this would only happen with Chinese voice. I tried some English voice, but they still didn't use. Ask the developer to fix this bug. I'm really looking forward to this app.
enes deniz
Yes, I understand what you mean better now.
But I don't think Adi can do anything about this.
We need to report these kinds of errors directly to the Read Speaker company.
Right, but it's far easier for Adi as a developer.
Adi is the developer, or at least one of the developers, of the iOS app.
is beta 3 is the final beta before it released to public ?
since IOS 27 is going to be released.
will it have next beta?
Beta 4 is available
Dear AppleVis community,
We have released a new beta, and it is packed with lots of good stuff. Here is the full list of changes.
User dictionaries feature
We have added a basic user dictionary feature, available from the settings tab. With this feature, you can add pronunciation rules for various words that are incorrectly read or you want to tweak.
For the first version, the dictionary is very basic, allowing you to just define rules, which apply to all voices/languages. Later we will extend this to be able to select only specific voices/locales.
We have also added the ability to import/export dictionaries, and the files are going to be cross compatible with our Windows version.
Voice profile import/export
We now allow importing and exporting voice profiles. Note: these wonβt be compatible with our Windows version, since we also have Vocalizer voices there, and other differences.
Improved character pronunciation for lots of languages:
We have significantly improved character pronunciation for many languages β European languages, Arabic, Hebrew, Russian, Ukrainian, and others. This includes special cases like Arabic numbers, Hebrew characters, characters with vowels, and much more. We still need to improve Asian languages, as well as to clean up languages like Spanish, but it should be much better.
Text processing features:
We have added various text processing features, for situations where VoiceOver is not in use. These include our own punctuation processor, number processor, etc. These are not intended for VoiceOver, and I do not recommend enabling them.
Bugfixes:
We have fixed bugs causing strings to be truncated, a specially when they contained numbers. We have also made other reliability fixes, including a fix for a bug causing punctuation not to be read on the keyboard.
Please try this beta and let us know what you think.
android
please when is this getting to android
already download the latest beta and trying it.
just download the latest beta and trying it!
hope all is fine...
πππ
will it have NVDA add on ?
will it has the NVDA addon?
Importing voice profiles
Good day. Just downloaded the most recent beta onto an iPhone 15. Saw there was an option to import voice profiles. Is it possible to import voice profiles from apps such as Voice Dream and the like? if so, how does one go about this? Thank you.
Great progress!
Loving the updates that keep coming! Just checking, have you managed to fix the bug where it will still allow the screen to dim and lock in the midst of reading long text? I have my screen lock set to 30 seconds and find that I have to interupt speach routinely just to make sure that it doesn't cut off in the midst of what's being said. Any help with this would be greatly appreciated, though I know you also have many other bugs to fix. Thank you so much for all your work!
still freezing when reading a long artical or message
I am using IOS 27 and sometime when it read the long artical or messages and swipe right or left to read the next one or even open the apps switcher.
it would freez.
and I have to wait for a feww second to get it back and running and sometime I have to turn off voice over and turn it back on to fix it.
Windows and Android versions
Hello everyone. As per your questions, a Windows version is about to go online for everyone to try and buy either today evening or tomorrow morning. We have been selling it in Israel at first, which is the country where I live, and tomorrow I am expanding the rollout and making it international. It will allow to purchase either ReadSpeaker or Vocalizer voices, and is compatible with NVDA with a direct add-on, as well as JAWS via a direct driver, and SAPI5. Each engine, ReadSpeaker or Vocalizer, will cost $99. Of course this has nothing to do with the iOS pricing, which will be much lower. There will be a 14-day trial available. Android is starting internal closed beta testing soon, with a planned release sometime in October.
@ming
Hello I am checking the freezing with iOS 27 and will come back to you. Apple made some not so great changes there as per the way speech is used by VoiceOver in general. I'll come back regarding this topic.
@Adi Kushnir on Monday, September 7, 2026 - 06:15
thanks for your great work.
and also it's hapening when I change the language roter to one of the english voices like july and Kate...
and for the windows and NVDA version. I will try to buy it...
@Adi Kushnir
First of all, thank you for Beta 4; it's working great.
And about the NVDA addon, would you post us the URL, or create a forum post for it, since I can't seem to find the new version with ReadSpeaker support yet.
Thank you in advance
Mac version, please!
Just letting you know I'd instantly pay that $99 for a version that would run on my computer. It's a Mac.
I would instantly update my Mac OS version to something that would run it to do necessary beta testing if that would help.
The Windows version won't help me since I don't have a computer that can reasonably run Windows. Far too little RAM on my M1 Mac to be able to run a VM. And only fanless computers are acceptable to me.
Issue with the IOS 27
Hi all,
I am liking this TTS so far, and I wanted to make it my primary TTS. However, since iOS 27 launched and I installed it, I have been having a serious issue with the voice.
Sometimes the voice completely freezes and there is no speech response, even though VoiceOver is still enabled. When I am reading something, it suddenly gets stuck with no speech at all. I then have to turn VoiceOver off and turn it back on again to get the speech working.
This is happening quite frequently, and it is very serious and annoying, especially when relying on this TTS.
Has anyone else experienced this issue after updating to iOS 27?
A new beta is out
We have a new beta out for you to try. This build fixes various issues with iOS 27, such as voices getting stuck and requiring a Voiceover restart to start working again, as well as various pauses not being handled for punctuation. Also, the volume of the voices is increased.
question
Hi,
question: these voices are very cool. Have you decided the pricing yet on these voices? I don't have the money right now to afford extra voices so if I want to continue, can I just use the public beta for the time being and how long will the beta last?
Distortion
Don't know if it's because of how VoiceOver sounds on iOS 27 or you've increased the volume too much and it exceeds 0dB, but the voices sound distorted even when I lower the system volume. And don't know if it's me or everyone in general, but you have this tendency to ignore my feedback here and on TestFlight, so let's see what happens this time.
Clippingdistortion
Happening here as well. Julie is downright unpleasant now. It's so sad!
Pronunciations
I am so far liking this new build of Runa TTS. The English voices sound a lot more fluid and less broken than they did in the initial release. I do have a question regarding pronunciations. I see that there is now a community dictionary in the TTS application, my question is can we import pronunciations from VoiceOver to the community dictionary in Runa TTS?
voice replacement?
upon installation of this latest beta, all voicees I had previously installed were still there, along with the updated voices to download. why is this? can't the app detect which voices are installed for future enhansment, and replace voices from a previous build?
@Enes Deniz
hello. First of all, I would like to say that I am not ignoring your feedback at all, not here and not on TestFlight. I cannot comment on each and every post or feedback that gets sent, but be sure that all of the feedback, including yours, regarding all the specifics you have provided, is processed. there are things we can fix, others we can't, everything we fix is published here and I am actually now working specifically on things you have reported before. So you are not ignored. As per the distortion, please tell me which voice are you testing against. We have tested several voices before pushing this change specifically to avoid distortion, and they were fine. Also, please remember that iOS 27 has sound profile issues with VoiceOver in the public release. Please let us know what is distorted for you.
Daniel Angus MacDonald
Hello Daniel. You do not need to replace any voices, since none of them got updated. The app shows all voices, with an "installed" or "available for download" status, base don the actual status of each voice.
Faerie
Thanks for pointing out a specific voice. We will look into it.
@Brian
The formats of VoiceOver dictionaries and ours are different. We will see what we can do.
Re: @Brian
I should mention that, as someone based in the United States, UK English voices are still replacing, "AppleVis", with, "AppleVista", even though I have set up a user dictionary for that specific word.
Just FYI.
Re: @Brian
I'm currently testing Bridget enhanced as my primary VoiceOver voice, and it's speaking AppleVis correctly. Maybe remove the dictionary entry in case that's now interfering with things π€
Re: Daniel Angus MacDonald
that's good to know
Re: @Brian
What region are you in? Asking because if you are, say in the UK, then the UK voices will work fine pronouncing AppleVis. Also, the UK voice, Mia, was a fresh download for this new build of Runa TTS, I only added the user dictionary after initially hearing her mispronunciation of the website name.
Answering a question while asking one of my own
Regarding the distortion issue, I would rather avoid naming a single voice as the culprit, because it could occur with any voice, but I use Ozan (enhanced) myself and he sounds distorted. As for my own question, can or should we really update the voices after updating the app itself? I refreshed the catalog but still have no duplicates. And why do I even have to refresh the catalog manually in the very first place? Can't the app do that automatically and just inform me if there are any new voices available, just in case I wish to download them? Finally, since you said I wasn't ignored, let me suggest that you add a heading to separate the installed voices and downloadable ones. We can just jump to that heading to skip directly to the downloadable voices to download any of them, without having to go through the voices that we've already installed.
Re: Enes Deniz
Hello. As per updating voices, you do not have to do that, whenever there will be a need, you will be informed in the app. The refresh catalog button is there for testing purposes for now, to force updating the latest voice data from the server, in case it does not show up for some reason. As per splitting between installed voices/the ones available for download, this is coming with some other UI changes. Stay tuned.
Is this the same as?
Is this the same as runa tts sold by orbit research?
Meaning does it have the same voices? I'm trying to figure out if they're the same product, or 2 products sold by different names.
distortion
I am experiencing distortion, using the Erin voice.
Julie says apple vista
Subject says it all. It doesn't really bother me but just in case it helps pin down the bug. I have made no changes to my dictionary. Also I have reverted back to the previous build because the clipping/distortion seemed to be happening among many people and it was very unpleasant.
@techluver
Orbit Research is selling our Runa TTS product but for Windows. This is the same but for iOS.
Distortion
Hi folks. Thanks for all the feedback regarding the distortion. We cannot reproduce it on the hardware we have here, but have noted it and will revert the change in an upcoming build later today.
Re: Windows and Android versions
I'm sorry for posting the same question repeatedly, but any updates on the windows version?
I've seen ver 2.0 on region-specific sites, but can't seem to find it on the international page.
I have this issue too
I have this issue too.
In addition I have an issue about pronouncing uncorrect the latter A.
It sounds as I.
Turning up the volume wasn't a good idea
Hello.
Iβve been hearing about the same audio distortion issues from friends around me who use this product. In my opinion, there was no need for the audio boost update at all, and I think it would be better to roll it back.
@luca
hello. Yes, version 2.0 went out in Israel first, my own country, where I have conducted testing and have done lots of improvements as a result. Next week you will see it internationally on our partners page, Orbit Research. A dedicated AccessMind website will be internationally updated at the end of October. Until then, Orders and testing can happen through Orbit Research. I will notify.
Re: @luca
Hi, thank you very much for the information.
I look forward to using the Windows version, since it's perfect for my phone.
Another beta is out
Hi folks. We have another beta out.
With this beta, we have Improved character pronunciations, Roled back the audio boost change, improved general engine performance, and optimized performance of voice profiles.
better feedback
I have noticed that not everyone specifies the iOS version and device they are using when complaining about sound quality. I think it would really help clarify the issue if the Runa TTS test version, the iOS version number and whether using the latest OS beta or the released version.
Those details can really make a difference, especially this year.
Voice quality
Really liking this new build so far. I have downloaded all of the US English and US Australian voices, and there's really only two voices I don't like.
Australian Mason.
US Mark.
These two voices do not sound that great, even the higher quality versions, on my device, which is an iPhone SE 2022 running iOS 26.7.
Also, the Australian voices are still pronouncing AppleVis as AppleVista.
@brian
You can use the user dictionary feature to fix this.
Re: @brian
Not working. Let me describe my steps below, and you could tell me if I am doing something wrong.
First, I set it to the voice I want to use, Mia (English Australian) in this example.
Next, I opened the RUNA TTS application, and double tap on the settings tab at the bottom of the screen.
Here, I navigate to the user dictionary and double tap, then I double tap again on the Add dictionary entry button.
On the screen, I type in the word applevis, in the first text field. In the second text field I spell it, "AppleViz" (Note the spelling).
Finally, I double tap on save in the upper right corner. I should also note here that I leave case sensitivity set to "off".
After all that, when I visit this website, the logo in the upper left corner of the webpage still reads as, "AppleVista logo".
ARIA Label
Yeah, I know this sounds geeky, but you can inspect the source code and check the ARIA label. Perhaps the two words are separated by a space.
Re: ARIA Label
@Enes,
A good thought, and it looks like the words do have a space between them, so, "Apple Vista", rather than, "AppleVista" (note the difference in spelling).
I have tried the following pronunciation changes in the user dictionary with no success:
*Vista to*Viz
*Vis to *Viz
AppleVis to AppleViz
AppleVista to AppleViz
So far no luck. π£
I should note here that this only affects English voices that are not United States based. As those seem to work fine. I am guessing that this is region base, because I have seen others report that some of the US based voices are doing this for people that are not in that region. π€·