Jasper
AI
voice assistant
SHOW HN2014
How HN took it
13 positive, 34 neutral or asking, 2 mixed, 2 critical, out of 51 comments about the project. Thread score +0.24.
Idea: 7 for, 0 againstExecution: 3 for, 0 againstDocs: 2 for, 0 againstPricing: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clean, well-structured, well-documented code
From 3 comments
Nice project--I like the code, it's very clean and well structured. You should check out the subversion trunk of pocketsphinx, it has support for keyword spotting built in so you…
tdicola on HNSeems clean, useful, and well-documented!
nmadhavan on HNExcellent work, I've always wanted to see a real world use of pocketsphinx with python. When I looked a year ago the documentation was lacking. The module system looks nicely…
jkldotio on HN
Useful open-source project pitched like a product
From 1 comment
Open Source project pitched like a product. This is how you do it peeps! I like this a lot and I'm encouraged to see it.
achalkley on HN
Objections
Text-to-speech quality is poor compared with commercial assistants
From 1 comment
It's a shame that the quality of open-source text to speech engines is so much worse than the current commercial state of the art, as that's the most notable difference in the…
apendleton on HN
Some binaries are needed despite claim of fully open source
From 2 comments
It says it's 100% open-source, but I can't seem to find the sources for the Jasper platform (not the Jasper client). Even the "compile Jasper from scratch" installation method…
scribu on HNOk, but why do I have to both install some binaries and clone jasper-client? http://jasperproject.github.io/documentation/software/#install-binaries…
scribu on HN
Raspberry Pi may be overpowered and overpriced for this task
From 1 comment
I think this is a great project! But Raspberry Pi might be a bit overpriced/overpowered for this task. Maybe something like Arduino Yún would be more appropriate choice. I am…
bliker on HN
Requests
Support for other languages and acoustic models
From 2 comments
That's amazing, I'm impressed. I have no idea how voice recognition software works, but is it possible using this open source project to add other non-Latin languages (e.g.…
atmosx on HNI need a french acoustic model, if anyone has one...
smallfluffycat on HN
Better installation documentation
From 2 comments
Ok, but why do I have to both install some binaries and clone jasper-client? http://jasperproject.github.io/documentation/software/#install-binaries…
scribu on HNthis might be a stupid question but HOW! :) after some troubles I finally got Jasper to boot up and first thing he does is complaining he can't connect to a network. So I connect…
hansch on HN
Offline operation for media control
From 1 comment
I would love if that worked offline, too. Even if it is just a very limited use of voice recognition. Like, Siri has to be online cause everything is processed on Apple's servers…
yaeger on HN
Questions
Whether it works over a wired connection without wifi
From 2 comments
I'm not entirely clear on why it requires a WiFi adapter? Can you not use the wired connection? Module writing looks pretty nifty though, can't wait to give it a try over the…
m4r71n on HNthis might be a stupid question but HOW! :) after some troubles I finally got Jasper to boot up and first thing he does is complaining he can't connect to a network. So I connect…
hansch on HN
Recognition distance and accuracy
From 2 comments
Great work! What sort of recognition distance were you able to get with that microphone?
tylercrumpton on HNHow accurate is text recognition (could you use it for dictation?) and how fast between the end of a command and recognition/parsing of said command?
drincognito on HN
Alternatives named
Wit.ai for natural language processing
From 1 comment
I actually made this exact thing Saturday afternoon. Great job! First prototype was on an Arduino it and eventually ran out of firmware space. So then I upgraded to the RPi and…
kyle_martin1 on HN
Festival or Android picoTTS for speech output
From 2 comments
And use festival, not espeak!
fixedd on HNThis is pretty cool. I would use Android's TTS (picotts). Audio quality is better.
izqui on HN
Google TTS
From 1 comment
You can use Google TTS. It doesn't have a documented public API, but nor did Google Reader.
AndrewHart on HN