Comments
Hi @peterhartree, I'm getting an error when trying to open the voting form:
"You need permission - This form can only be viewed by users in the owner's organization."
Hi @peterhartree, I'm getting an error when trying to open the voting form:
"You need permission - This form can only be viewed by users in the owner's organization."
Fixed—thank you.
Thanks for all your hard work on the audio narrations and making EA Forum content accessible!
Question: Do you intend to license the audio under a Creative Commons license? Since EA Forum text since 2022 is licensed under CC-BY 4.0, all that's legally required is any attribution info provided by the source material and a link to the license; derived works don't have to be also licensed under CC-BY. However, to the extent that AI-generated narrations can be protected by copyright at all (e.g. in the UK and Hong Kong), it seems appropriate to use CC-BY, or maybe CC-BY-SA to enforce modifications being under the same terms.
The results of the listener survey were equivocal. Listener preferences varied widely, with Ryan (our existing voice) and Echo coming out tied and slightly on top, but not with statistical significance. [1]
Given that, we plan to stick with Ryan for now. Two considerations that influence this call, independently of the survey result:
We'll survey again—or perhaps just switch based on our judgement—when better models are released.
[1] Above a basic quality threshhold, people's preferences for human narrators also seem to vary wildly. We've found that the same human narrators elicit feedback that can be characterised as "love letters" and "hate mail"—in surprisingly similar proportions.
We make AI narrations of EA Forum posts available via our audio player and podcast feeds:
EA Forum (Curated & Popular)
Curated posts and posts with 125+ karma.
Apple Podcasts | Spotify | RSS | Other platforms
EA Forum (All audio)
Curated posts and posts with 30+ karma.
Apple Podcasts | Spotify | RSS | Other platforms
We’re thinking about changing our narrator’s voice.
There are three new voices on the shortlist. They’re all similarly good in terms of comprehension, emphasis, error rate, etc. They just sound different—like people do.[1]
We think they all sound similarly agreeable. But, thousands of listening hours are at stake, so we thought it’d be worth giving listeners an opportunity to vote—just in case there’s a strong collective preference.
Please listen here:
And vote here:
It’ll take 1-10 minutes, depending on how much of the sample you decide to listen to.
Don’t overthink it—we’d just like to know if there’s a voice that you’d particularly love (or hate) to listen to.
We’ll collect votes until Monday December 16th. Thanks!
We’re always keen for general feedback on the narration service. Please do share thoughts on the form, or in the comments on this post.
We periodically the various text-to-speech services, with a particular focus on ElevenLabs, Speechify, Azure, Amazon, BeyondWords, OpenAI, Murf.ai, Play.ht, Deepgram and a few open source libraries. The current shortlist was created based on factors like performance, reliability, customisation options and price. We won’t consider other voice options this winter, but if there are other voices you particularly like, please do let us know, and we’ll make sure they’re considered in future reviews. ↩︎
Happy to see more work here.
Minor question - but are you familiar with any experiments that might show which are the most understandable, especially at high speeds? It seems to me like some voices are much better than others at 2x+ speeds, I assume it should be possible to optimize this. This is probably the main thing I personally care about.
A long overdue thank you for this comment.
I looked into this, and there is in fact some evidence that less expressive voices are easier to understand at high speed. This factor influenced our decision to stick with Ryan for now.