I wish there was a reader app that was serious about text speech. This is not it, unfortunately. Reader apps need to focus on a text to speech experience that is identical to a music player so that you can use the app while in hands free situations. The app is also hard to use as a “read it later” tool on iOS. I was really hoping they would fix these issues by now because it was promising. This app truly does feel li…
Have you used it? I use it for both hands free and read later. When I'm on a webpage I just use the safari share sheet to send it to ElevenLabs Reader and then just listen whenever I have time.
You should try it with your own voice! (By first creating a custom voice on the web interface. The quick basic clone should be enough). I found that it’s my preferred way to use their reader, as it makes the reading more neutral and transparent for my brain.
Most people don’t like hearing their own voice (how it sounds like in reality, not in your head).
I wish there was a reader app that was serious about text speech. This is not it, unfortunately. Reader apps need to focus on a text to speech experience that is identical to a music player so that you can use the app while in hands free situations. The app is also hard to use as a “read it later” tool on iOS. I was really hoping they would fix these issues by now because it was promising. This app truly does feel li…
Have you used it? I use it for both hands free and read later. When I'm on a webpage I just use the safari share sheet to send it to ElevenLabs Reader and then just listen whenever I have time.
Let’s say I have article 20 article articles of two minutes length each. On the iOS app, there are no next buttons and it does not automatically play the next article. If I am on a long drive, or I am running for two hours with my phone in my bag, I would need to reach into my bag and open the app every time and click the next article. If I I don’t like the article I am listening to, there is no way to skip to the next article using integrated controls on a Bluetooth device. These features already exist on apps like Pocket.
I was briefly excited to try this on out-of-print books I find on Google Books, but alas the OCR in Acrobat PRO is super glitchy. I need to find some AI-assist OCR to fix tons of mistakes like "186o" for 1860 or "gla)" for glad.
> On my M2 MacBook Pro, on CPU, it takes about 1 hour, at a rate of about 60 characters per second. Umm, it does.
My bad. I misread the official website: > We don't currently support Apple Silicon, as there is not yet a Kokoro implementation in MLX. As soon as it will be available, we will support it. I thought that meant that it didn't support Apple Silicon in general, but they were just talking about GPU support.
though they wouldn't need to use MLX, could also use pytorch etc
Zonos is a new open weights text-to-speech model that has quality at least as good as ElevenLabs: https://www.zyphra.com/post/beta-release-of-zonos-v0-1
TTS is increasingly being commoditized. Kokoro was posted and it works on webgpu, absolutely incredible quality for where it can run https://news.ycombinator.com/item?id=42973769
Kokoro hasn't released their encoder, but they are already moving on to a newer model. Hopefully they release that!
I was briefly excited to try this on out-of-print books I find on Google Books, but alas the OCR in Acrobat PRO is super glitchy. I need to find some AI-assist OCR to fix tons of mistakes like "186o" for 1860 or "gla)" for glad.
I made a site like that, fixmydocuments.com Also check out my open source project for that: https://github.com/Dicklesworthstone/llm_aided_ocr
Will definitely check it out.
Hyphenated words, page numbers and chapter titles seem to be my main issue. I can easily do search and replace on chapter titles though.