I had a chance to check out the service called Slidespeech.com.
Slidespeech is an online service where you can upload Powerpoint, Google Doc, ODP presentations and their service will auto narrate whatever is written in the speaker notes area and create an autorunning video-esque presentation that can play back through slidespeech.com or through their app on mobile devices (iOS & Android)
So, how does it work? well… a little clunky. But, let me preface the rest of my comments with the fact that Slidespeech is currently in their alpha version, so it’s expected that there would be a lot of bugs to work out before they hit Beta… where they will work out even more bugs, before it’s officially released.
So I created a fake account with slidespeech.com and uploaded a PPT file that had speaker notes. Here is what happened:
- Imported presentation lost all transitions and a lot of visual effects that were on screen. Some graphics and text effects were not properly converted. That said, most of the presentation translated fine.
- During playback, any slides that did not have speaker notes were immediately skipped over. They autoadvance the slides after the speaker notes are finished being narrated… no narration = skipped slide
- The presentations played back nicely on the computer as well as the iPad. (did not test on my android phone)
- The speech engine works… ok. the accent is a little odd. Sometimes you may have to spell out words in your notes area phonetically so that the speech engine can read it properly. It behaves a lot like what you would hear on an Xtranormal video. (Example of xtranormal video on my iPad app blog post: http://is.gd/VE7i1l)
So… my verdict? It has potential, but isn’t ready for primetime yet. … and I’m left wondering if the time spent writing a machine readable narrative in the notes area couldn’t be better used to simply record your own narration using the built-in tools in Powerpoint…. then there would be extra control over slide timings…
One Comment
Tom –
Thanks for trying SlideSpeech. These are early days for us. SlideSpeech was founded in February 2012.
One million Android devices activate every day now. A global transformation is underway, particularly in the developing world.
Many people have wondered why SlideSpeech uses text-to-speech when you “can” record your own narration (despite this capability, very few people ever use PowerPoint’s narration feature). On Android we have implemented a HUGE bandwidth saving strategy: by sending only slide images (with no transitions) and the script to the phone, and then using the text-to-speech engine to speak the script there, we save 90% of the data traffic of the equivalent audio or video. Low bandwidth usage is key to reaching developing markets like India and China — or any place that charges for mobile data.
Control of the playback is coming in our next release. Playback control adds a whole new dimension over the passive, play-until-it-ends modality of video. Please take a look at this prototype in action on YouTube: SlideSpeech Medicine. The interactivity is driven by a typed script. And we have worked out how those interactions can include links. With links, we can build a system which verbally guides you to appropriate material. So ultimately a whole system can be collaboratively created using text — just like Wikipedia. You can’t collaborate in the same way with recorded audio or video.
So, yeah, we see some potential here too!
Please try out some simpler presentations on people far away. This is easy: just forward the e-mail response you get from the SlideSpeech server. I find I can save a trip by just sending a quick and simple SlideSpeech presentation instead. It is a “talking e-mail message.”
You might also try out our embed feature, to show off the example presentation you made.
Cheers,
John