Live data from Hacker News

ElevenReader

elevenreader.io

151–160 of 183 posts

Re: ElevenReader

#151
post #115

Earlier quoted context omitted.

Wow really? I use it all the time for ~equivalent activities

How long are the articles you are reading? I’m reading blog articles rather than long form content. My queue is in the hundreds and the articles very in length from two minutes to 20 minutes. I found it really annoying to need to push buttons while driving to skip or auto play the next article.

Yeah, mostly super long form stuff. If it's only 2 minutes it's faster for me to just read it than to open it in their reader

Fwiw, I would use their app way more if it were better. Right now I use it for 1-2 long form articles at a time, I am sometimes willing to push buttons in order to stay focused but will bail out to eg my podcasts app if that becomes untenable

Re: ElevenReader

#152
If you want free/ultracheap, the Google Cloud TTS is good enough for simple use cases. You get enough free minutes that it may end up being free (I think I've paid a cent so far).

Some of their voices sound very artificial, some very real. I've been slowly making a list of the good ones.

I use it to convert long articles into audio, and have a script to add it to my podcast feed to listen to while driving:

https://blog.nawaz.org/posts/2024/Apr/reading-articles-via-p...

Re: ElevenReader

#153
post #102

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

Hey, they are using Mamba! Happy to see Mamba is used at least somewhere :/

Re: ElevenReader

#154
Honestly, why isn't this same service baked into my OS? the reader there is really atrocious, but I imagine even for a single voice a pretty small model can be downloaded and made available as a plugin for the reader app.

Re: ElevenReader

#155

If you want free/ultracheap, the Google Cloud TTS is good enough for simple use cases. You get enough free minutes that it may end up being free (I think I've paid a cent so far). Some of their voices sound very artificial, some very real. I've been slowly making a list of the good ones. I use it to convert long articles into audio, and have a script to add it to my podcast feed to listen to while driving: https://bl…

Chirp (HD) gives you $30 per 1M characters for free on the free tier also

Re: ElevenReader

#157

If you want free/ultracheap, the Google Cloud TTS is good enough for simple use cases. You get enough free minutes that it may end up being free (I think I've paid a cent so far). Some of their voices sound very artificial, some very real. I've been slowly making a list of the good ones. I use it to convert long articles into audio, and have a script to add it to my podcast feed to listen to while driving: https://bl…

Chirp (HD) gives you $30 per 1M characters for free on the free tier also

I'd have to analyze my usage. For me, having used it for over a year cost me a penny. If I can ensure my total cost is less than $1/month, I'll consider it if the quality is really good. The Google one is "good enough", but not great.

One other feature I'd really like: Having the AI figure out who is saying what and use different voices (e.g. one voice for overall narrator, and separate voices for each person who is quoted in the article).

Not sure if any of the solutions out there do that automatically without my guidance.

(Still probably wouldn't pay more than $2/mo for it - I just don't use it often enough to justify paying much).

Re: ElevenReader

#158

Earlier quoted context omitted.

Chirp (HD) gives you $30 per 1M characters for free on the free tier also

I'd have to analyze my usage. For me, having used it for over a year cost me a penny. If I can ensure my total cost is less than $1/month, I'll consider it if the quality is really good. The Google one is "good enough", but not great. One other feature I'd really like: Having the AI figure out who is saying what and use different voices (e.g. one voice for overall narrator, and separate voices for each person who is…

The audio quality is amazing. It's transformer based. I use it occasionally

Re: ElevenReader

#159
post #78

Earlier quoted context omitted.

I understand, It can do things that weren't previously possible, but it will also replace things that were done by humans, by artists before. Overall, in my opinion, is still a loss.

I think calling this art is a stretch, as they usually aren’t the author. By automating it, it lowers the barrier to access this type of audio content for the masses. If you want to choose to pay someone you read something for you, the market allows that. This feels like a net gain.

> I think calling this art is a stretch, as they usually aren’t the author.

So I guess in your worldview a concert violinist also doesn’t make art, when they are playing a Mozart composition?

Post reply on HN