manton
manton

This blog post is a test for something new I’m working on. I think a lot of people feel overwhelmed that AI is everywhere right now. Personal blogs should lean in to the human voice. There’s a new play button on the permalink for this post on the web which will use a recording that I’ve uploaded.

|
Embed
Progress spinner
vincent
vincent

@manton Amazing!

|
Embed
Progress spinner
g
g

@manton Love it!

|
Embed
Progress spinner
jabel
jabel

@manton Cool!

|
Embed
Progress spinner
aeryn
aeryn

@manton Woah! I likey

|
Embed
Progress spinner
phils@social.lol
phils@social.lol

@manton how many people are going to say that’s really good training data for a voice model…. But it was nice to hear your personal voice, as another human.

|
Embed
Progress spinner
vincent
vincent

@phils there will be these people... sigh.

|
Embed
Progress spinner
reesericci@social.hardfork.ngo
reesericci@social.hardfork.ngo

@manton nifty!

|
Embed
Progress spinner
manton
manton

@phils Thanks! Yep, it's a great question. Voice models are about to get very, very good. But they're still not me.

|
Embed
Progress spinner
jimmitchell
jimmitchell

@manton Pretty wild. Looking forward to seeing more on this one.

|
Embed
Progress spinner
pratik
pratik

@manton How do we know you recorded that audio and are not using AI that used your voice to train it? 🙃 With your podcasts, I bet it’s pretty easy to do and quite accurately.

|
Embed
Progress spinner
manton
manton

@james I had a bug with dark mode that I just fixed. Maybe that was it?

|
Embed
Progress spinner
manton
manton

@pratik Heh. Well, the mistakes I didn't edit out this time. 🙂 But yeah, synthetic voices are getting incredibly good.

|
Embed
Progress spinner
js@podcastindex.social
js@podcastindex.social

@manton @james

it's over here with all of the comments

manton.org/2024/05/24/this-blo

|
Embed
Progress spinner
manton
manton

@james Oops, I see what happened. The “transcript” link messed up the post on Mastodon. Fixed going forward.

|
Embed
Progress spinner
pratik
pratik

@manton But jokes aside, if I train an AI model with my voice and use it for such post narration, is that not using AI "correctly"? It will save me tons of time and yet personalize my blog posts. Heck, I don't mind (in fact, prefer) if it preserves my stutter.

|
Embed
Progress spinner
manton
manton

@pratik Maybe it’s like alt text: hand-written alt text is great, but AI-generated text is so good why not use it so that it’s accessible to more people? Likewise maybe in the future all posts will have synthetic narration by default but humans can override as needed to provide their own audio.

|
Embed
Progress spinner
canion
canion

@manton I love this. What a cool feature; hope it’s able to be released soon!

|
Embed
Progress spinner
numericcitizen
numericcitizen

@manton I'm anxious to try it as soon as my visual theme is updated by @Mtt and @ericgregorich !

|
Embed
Progress spinner
ericgregorich
ericgregorich

@numericcitizen @manton cool feature. I’ll update the Cards Theme with support for it when it’s released.

|
Embed
Progress spinner
Mtt
Mtt

@numericcitizen Tiny will definitely support it.

|
Embed
Progress spinner
pratik
pratik

@manton Yup. Auto-generated (in my voice) but the option to override specific posts in case I want to do it in a different tone/mood/impression.

|
Embed
Progress spinner
jimmitchell
jimmitchell

@manton This is cool work. Out of curiosity, in your example post, is AI transcribing your voice input? To me it sounded very much like you were reading the post as if it were already written. If it was transcribed, how did you handle the screenshot image insertion? Was it the little “screenshot here” aside? Finally, does the transcription save as a draft to clean up then manually post? Sorry for many questions.

|
Embed
Progress spinner
manton
manton

@jimmitchell I wrote the blog post myself, then read it, but funnily enough after I posted it Micro.blog did transcribe the audio back to text with AI. In this case, that was redundant, so the transcript can be tossed.

|
Embed
Progress spinner
jarrod
jarrod

@manton @pratik That's exactly what I've been dreaming of.

|
Embed
Progress spinner
pratik
pratik

@manton So would it make to first make audio “post” and then have AI transcribe it? ☺️@jimmitchell

|
Embed
Progress spinner
In reply to
jimmitchell
jimmitchell

@manton Interesting. I can't seem to find any transcriptions for my tests on my test micro.blog. Are you dumping them as part of the feature, or have I missed something? Will the feature ever get to the place of being able to upload audio and the post gets transcribed?

|
Embed
Progress spinner
manton
manton

@jimmitchell One limitation that you might be hitting: we only transcribe one audio file per day. I was worried about the costs, but it has been fine so I'm going to raise that limit this week. If you click Transcripts, you can delete previous transcripts to work around the limitation for now. Also, check Account → View logs. It has log entries specifically for transcripts.

|
Embed
Progress spinner
manton
manton

@pratik Yes, I actually do this pretty often! Upload audio to my test blog, grab the transcript, then delete it.

|
Embed
Progress spinner
manton
manton

@jimmitchell Also check out the other limitations in the documentation. For example, it only works with MP3 files.

|
Embed
Progress spinner
jimmitchell
jimmitchell

@manton What? RTFM? Never! 🤣

Thanks. That clears things up a lot and explains why I didn't see a transcript, since I uploaded in .m4a format.

|
Embed
Progress spinner
pratik
pratik

@manton I'm more of a writer than a talker, so the opposite would work for me, but for people who do what you do, perhaps it can be made more automated?

|
Embed
Progress spinner