Create a WebRTC Video Chat App With Speechly Transcription
Learn how to build a WebRTC video chat application that uses the Speechly Browser Client to transcribe audio from a MediaStream.
Mathias Lindholm
May 24, 2022
8 min read
Everyone who has built a robust natural language user interface, be it a voice UI or a chatbot, knows that getting all the details right can take quite a bit of work and iterations. Also, while most tools for building natural language UIs are designed around the same principles (intents and entities/slots), getting to grips with the intricacies of each platform can be similar to learning a new programming language.
Hence, to lower the barrier of entry to Speechly from legacy voice UIs, we are excited to introduce a new feature that lets you create a new Speechly application from an existing Alexa skill in a few simple steps. With this feature, folks can easily turn their Alexa skill into a streaming Speechly voice application that can then be used to enable Reactive Voice UI experiences on the Web.
At the time of launch, we support the following Alexa slot types:
AMAZON.NUMBER
(mapped to SPEECHLY.NUMBER
)AMAZON.ORDINAL
(mapped to SPEECHLY.SMALL_ORDINAL_NUMBER
)AMAZON.DATE
(mapped to SPEECHLY.DATE
)AMAZON.TIME
(mapped to SPEECHLY.TIME
)AMAZON.PhoneNumber
(mapped to SPEECHLY.PHONE_NUMBER
)
(Note that there may be small differences in the way the returned slot values are normalized.)Good to note: as per Speechly’s single-turn Reactive Voice UI paradigm, the conversion feature does not support dialogue management features that Alexa skills sometimes rely on. The resulting Speechly application can recognize the intents and slots as they appear in the Alexa Interaction Model, however, Speechly will not trigger follow-up questions for instance if the user’s utterance is missing a required slot.
If you are new to Speechly, take a look at our Design Philosophy Guide. There you will find guidelines and best practices for creating websites & applications with Reactive Voice UIs.
We believe that this feature is useful for those of you who have heavily invested in developing Alexa skills, but would still like to give Speechly a try. This will be especially useful when you are interested in evaluating Speechlys NLU accuracy on your application. (An arguably necessary step to take when considering any new voice UI platform.)
The feature is now released as a public beta, and we are happy to receive feedback on how to make it more useful for you. Likewise, please let us know if you would need support for other platforms in addition to Alexa.
Start developing today with Speechly, see our demos, and check out our documentation.
Amazon Alexa and all related logos and motion marks are trademarks of Amazon.com, Inc. or its affiliates.
Cover photo by Jessica Lynn Lewis from Pexels
Learn how to build a WebRTC video chat application that uses the Speechly Browser Client to transcribe audio from a MediaStream.
Mathias Lindholm
May 24, 2022
8 min read
Abandoning the Voice Assistant model for a Voice UI as a Feature results in the most efficient UI since the Touchscreen.
Collin Borns
May 12, 2022
2 min read
From Punched Cards to Touch Screens, User Interfaces have evolved significantly. Will Voice be next in this evolution?
Collin Borns
May 11, 2022
4 min read