I am working on a story, that Pepper tells. This story has 4 characters - 2 men and 2 women. Is it possible to make Pepper sound like a men / women while speaking.
You can change the pitch of peppers voice to sound more male/female.
To change the pitch in choregraphe you adjust the Voice shaping parameter.
If you are coding in python then the syntax is:
tts.say("\\vct=150\\My name is Juliet")
tts.say("\\vct=50\\Now I am Romeo")
Some more details on the voice shaping here.
The same syntax can be used in Dialog scripts.
Related
I want to create a change voice function for a meeting application using webrtc.
I have 2 solutions for it:
Solution 1: Use MediaStreamAudioSourceNode and connect node to create audio filter
https://github.com/mdn/webaudio-examples#stream-source-buffer
But I can't control the sex of voice.
Solution 2: I use speech to text and text to speech.
I use speech to text to get the content of the speaker.
Afterthat, I send text to another member in meeting. And use text to speech to create voice.
But the transmission speed is slow and inaccurate in terms of content.
Do you know any AI or library that supports this?
I want to change the map in Rainbow Six Siege like when i start any map in custom game and load any other map.
Please Help 🥺
Example: I select House Map in custom game And Change something from cheat engine or change some hex codes then start i get bank map.
Go to options and select matchmaking preferences then you can disable all the ones you don't want to play and leave on the ones you do. Effectively you can just do one map and one mode if you desire. This works for Lone Wolf and PVE. Video below shows how.
https://youtu.be/KUn-zdRob8M
hope u r satisfied with the answer
Is it possible to change the voice alexa is using within my skill?
i.e. the user asks
Alexa Ask Car Washing when the next available appointment is?
and have Alexa respond with a voice that matches my carwashing brand?
Yes, it is possible.
You can use SSML Tags in output speech response of your skill to achieve this.
You can
whisper
put emphasis on a word or phrase
use different languages like French, Spanish etc.
different voices and many more
For Example
<speak>
Here's a surprise you did not expect.
<voice name="Kendra"><lang xml:lang="en-US">I want to tell you a secret.</lang></voice>
<voice name="Brian"><lang xml:lang="en-GB">Your secret is safe with me!</lang></voice>
<voice name="Kendra"><lang xml:lang="en-US">I am not a real human.</lang></voice>.
Can you believe it?
</speak>
Learn more about Using SSML Tags HERE
I would like to capture anything a user says to Alexa in text form. Exactly how 'Alexa, Simon says...' works. Can someone hint at how that intent can be implemented?
I looked at this, this and this but the suggested answers don't work for me and there are no concrete 'accepted' answers to any yet.
LITERAL slot type works as long as the sample utterance is specified (i.e. hard coded literally). Like the answers suggested in the above threads, I tried to 'train' by providing 400+ combinations of possible utterances hoping that it will somehow figure out the rest of the combinations. But, no dice.
My input could be as random as 'TBD-2019-UK', '17_TBD_UK_Leicester', '17_TBD_UK_Leicester 1', '18_TBD_UK_Leicester 2', 'Chicago IL United States', etc. It is a pretty random combo of the year, city, state, country, some other key text in no particular order (lets ignore the special characters for now). Even if 'Chicago IL United States' is specified in Sample Utterances, LITERAL is not able to capture something like 'Pittsburgh PA United States' automatically unless that is also hard coded. There is no way I can come up with ALL possible permutations and combinations of year, city, state, country, some other key data points (... because it sounds impractical/ridiculous).
Plus, more values could be added by user. So it needs to be smart and dynamic.
The problem is, if there is no matching intent found for the utterance, instead of returning the user's speech text, my Alexa is just failing to do anything. It just goes off without doing anything. Any ideas?
Amazon's Alexa service is not designed for dictation. This has been the consistent response from the Developer Evangelists. So, quite simply, you cannot do what you desire: capture free form speech with wide variations.
There are various ways you can 'trick' Alexa into creating a 'generic slot', which I assume those links talk about. But, since it is outside the design parameters of Alexa, they will never perform well, as you have found.
For your use case, I suggest you break down your inputs into several exchanges. Don't use a one-shot invocation, but a dialog. For example:
U: Alexa, open spiffy skill
A: Welcome to spiffy skill. I'd love to do something spiffy for you,
but I need some information. You can give it to me by saying city,
year, state, or country followed by what you want me to look up.
U: City Cincinatti
A: OK, Got city Cincinatti. I need more information to be spiffy. How
Year?
U: Year 2010
A: OK, I've got Cincinatti, 2010. Should I look that up, or do you have
more info?
U: Look it up.
A: Got it. So for Cincinatti, 2010 ...
Is a wave limited to the sharing of textual information (HTML), or am I correct in assuming that a wave can contain arbitrary data (represented in XML), so long as it also contains the javascript necessary to render it in a meaningful way?
I ask because the collaborative document preparation demonstrated in the Google I/O video looks very powerful, but there are many other types of documents than simple rtf text. In my case I would be looking interactively to develop gantt charts.
There is a lot that can be done inside each Wave. They have not yet made all features available, but here is a link to some samples: http://wave-samples-gallery.appspot.com/ which includes my Slashdot Gadget:http://wave-samples-gallery.appspot.com/about_app?app_id=18006
The Slashdot Gadget actually takes the RSS feed for Slashdot and displays the latest headlines.
Here is the XML: http://www.m1cr0sux0r.com/slashdot.xml
alt text http://www.m1cr0sux0r.com/xml.jpg
I got access to Google Wave a few days ago, and here's what the raw data for their Sokoban game (which supports two players playing simultaneously on the same board) looks like, for example:
<blip>
<p _t="title">
</p>
<p>
<w:gadget author="blixt#wavesandbox.com" prefs="" state="" title="" url="http://sokoban-server.appspot.com/com.example.simplegadget.client.SokobanGadget.gadget.xml">
<w:pref name="playerAllocation" value="1 1,blixt">
</w:pref>
<w:pref name="totalMoves" value="8">
</w:pref>
<w:pref name="playerPositions" value="1 4,2">
</w:pref>
<w:pref name="rockPositions" value="6 2,2 3,2 14,2 15,2 16,2 4,3">
</w:pref>
</w:gadget>
</p>
</blip>
So yes, you can store any data you like in a single blip, with the possibility to go backwards in "time" to see older versions of the data etc.
By the way, if you're interested in seeing some code for a robot that sits in a wave and interacts with users, I made one for a game I'm developing: Google Code Project for multifarce (and the game in question, it's not really public yet and as such not particularly functional.) The bot source is here: multifarce Wave robot source
Basically, all you need to get a bot running are the 14 last lines in that code. I love it! =)