I would like my skill to be able to listen for specific responses, i.e. make Alexa bias towards utterances of one or multiple intents that I specify in the skill's response, for the next user input.

For example, let's say my skill has a CityIntent which has utterances:

• I live in {city}


• It is {city}


• {city}

And my skill has another MovieIntent which has utterances:

• I like {movieType}


• I prefer {movieType}


• {movieType}

And at certain times my skill may also expect {yes/no} answer from user.

Since {city} and {movieType} have different value, Alexa usually does a good job of figuring out which intent should be mapped.

However, sometime the single word utterances are incorrectly mapped to wrong intents, and there's very little or hacky way for my skill can cope with such cases.

Therefore I want my skill to have the ability to specify what the NEXT intention user is likely to make, at any point during conversation. Then Alexa can bias the listening towards the likely utterances and map to the correct intents.

I have looked into DialogModel, however it doesn't seem to be applicable because it doesn't allow switching intent, i.e. my code cannot be handling MovieIntent and then request Alexa to ElicitSlot for CityIntent.

Thanks!

Room awareness enhancement: add popular device types such as Fan, Air Conditioner, Set-top-box and let users change device type to their favorite. Now Alexa app allows changing device type between Light and Switch for some smart plug devices. But it would be great if for any device, users can define it as light, fan, air conditioner or set-top-box... and the room awareness feature will help simplify voice command. Users just can say: turn on the air conditioner, turn on the fan...
This device-type-changing feature will be very powerful when an infrared/RF universal remote control like Broadlink is connected to alexa. All traditional “dumb” devices can be voice controlled by alexa taking advantage of the room awareness feature.

We would like to use this, but can't because the rules are too restrictive.If a user is asked about what they want info about, they should not be forced to say "tell me about Point Defiance Zoo". They should be able to say "Point Defiance Zoo" with no leading phrase. Instead of forcing us to use a leading or trailing phrase, please allow the use of just {query} (without 'search for...' or other text around it as in the example below:

  {


    "name": "SearchIntent",

    "samples": [

      "search for {Query}",

      "find out {Query}",

      "search for {Query} near me"

    ],

    "slots": [

      {

        "name": "Query",

        "type": "AMAZON.SearchQuery"

      }

    ]

  }

The audio player interface allows playing from a streaming service - e.g. a radio station
This is a continuous stream that could run for many hours - but the skill is only given the opportunity to provide song information at the start.
It could respond to user requests - such as "What song is this?" (which is OK) but, primarily for devices with screens, it would be useful for the skill to be able to provide title/subtitle/graphics as the songs change within the continuous stream.

This could be done by having the Skill start the audio stream with a duration parameter which would result in a callback when it is about to be reached - similar to the PlaybackNearlyFinished request.
The Skill could then send new metadata (potentially with an offset to say display in X seconds) and with a new duration parameter.

An alternative approach that could work without any skill being developed at all ...
If the player automatically took the metadata from an ICY stream (as provided by Shoutcast / Icecast servers) then it would be a good alternative - especially if the skill to parse a regex that should be used to parse the ICY title - with a default that would handle "artist name - song title" which is what many internet radio stations use (and StreamURL for the image).
For example ...
Playing http://www.dandelionradio.com/DandelionRadio.pls.

Name : Dandelion Radio
Genre : Alternative
Website: http://www.dandelionradio.com
Public : yes
Bitrate: 128kbit/s
ICY Info: StreamTitle='Rocker: D. A. Stern - Isn't It Obvious?';StreamUrl='http://www.dandelionradio.com/images/drlogosq-black.jpg';

Currently, there is no way to accurately do automated testing of how user audio resolves (in terms of intents and slots) for a given skill.

At present, this testing is more-or-less done manually. There are several use cases where automation would be vitally important. Given:

-When testing a large skill, it is extremely cumbersome to manually test a wide array of sample utterances for every change we make to the voice model. This discourages iterative design.
-The overall Alexa voice model is constantly shifting. This is a good thing, but often this results in changes to how our skills launch utterances, one-shots, etc are resolved, and right now we have no way to do this testing on a regular, automated cadence.
-Testing a skill across a variety of voice types (varying gender, age, accent) is not something that we see done today, because the effort to manage something like that is considerable.

And, on a point unrelated to test automation, it would also be beneficial if we could have our users who are struggling with misfiring intents send us an audio clip of their voice and let us send that to this endpoint to see what's happening. Trying to reproduce a user's accent/pitch/prosody as a developer is (often comical, but) not particularly helpful.

All of these cases could be resolved by:
1. An endpoint within the SMAPI or some other similar REST service; which,
2. Accepts as a POST request an audio file in a specified format;
3. Along with whatever request metadata might be relevant; as well as
4. A parameter in the path or body that specifies the id of the skill under test; and
4. Returns a JSON object with the exact Alexa request that would've been made to the specified skill

Ideally this API could also have a mechanism for dealing with things like sessions and dialog management (and how the intent resolution may change in that state), but the 90% case could be easily covered by a simple "isNewSession" flag that lets us emulate both one-shots and open session requests.

It's worth noting that we've actually tried (with some success) to solve this problem on our own - to middling success - via AVS. The functionality just does not exist for this to be addressed by third parties, unfortunately. A description of our feeble attempt can be found here: http://www.3po-labs.com/blog/a-proof-of-concept-and-its-roadmap