While Android has support for native speech recognition with Google, that's not a suitable solution for responsive voice-enabled user interfaces.
Fully streaming API for actionable and real-time results
Speechly can be configured to any use case with no data
Customizable Swift UI components for fast development cycles.
”It was an amazing experience using Speechly”
Submit your email address and get access to our platform
First, the Speechly SLU model is configured to your use case by providing it with annotated example utterances that your end-users will use. This model can be deployed in tested in under an hour. Then the model is integrated to your application and business logic is built to match the structured data that comes from the API.
Speechly SLU API returns user intent, entities and the transcription of what was said. For instance for the utterance 'turn off the lights in kitchen' the API would return 'turn_off' intent and 'kitchen' as the modifier (entity) for this intent, along with the transcription.
You can get started with our free tier. The pricing is based on the amount of data sent to our API and is very competitive. You can read more on the Pricing page.
No. Our approach is very different than question-turn based smart speaker platforms. We believe in real-time visual feedback, enabled by our fully streaming SLU API. You can read more about our approach in our blog.
We can build a PoC with you in a short time. Book a call with us and we can help you build a configuration in under 24 hours. Then we can proceed into integrating that into a PoC that typically takes about 1-2 weeks to complete.
Speechly published a whitepaper on how voice technology can benefit grocery retail market. The whitepaper is available completely for free, no strings attached!
Voice has certain advantages over traditional user interfaces. Leveraging these advantages can create unique user experiences in any industry or domain.
Speechly Spoken Language Understanding demos showcasing real-time visual feedback and multimodality