Picovoice Console is the platform for designing, training, and testing voice interfaces instantly in your browser. No machine learning skills are required. Simply describe what you need in plain text and export trained models. The models run entirely on-device using the Picovoice SDK on any of these platforms:
- Embedded platforms such as Raspberry Pi, NVIDIA Jetson Nano, and BeagleBone
- Android and iOS
- Modern web browsers
- Linux (x86_64), macOS (x86_64, arm64), and Windows (x86_64)
- Microprocessors such as Arm Cortex-A
- Microcontrollers such as Arm Cortex-M
Today we are announcing Picovoice Console’s public availability to all developers. Sign up and start building for free.
Using the Picovoice Console, you can create voice experiences similar to Alexa and Google. Unlike these services, models created using Picovoice Console can run entirely on-device while being more accurate.
Custom Wake Words
Picovoice Console empowers you to create custom wake words within hours rather than weeks. Sidestep the time consuming and expensive data-gathering phase. Simply type the wake phrase you want and export a production-ready trained model. You can test the created models within your web browser, no coding required!
The trained models are even more accurate than ones created using traditional methods relying on data gathering. This is achieved using a proprietary transfer learning algorithm developed by Picovoice.
Domain-Specific Intent Inference
Using Picovoice Console, you can create bespoke voice recognition models to infer a user’s intent from spoken commands. These models are tuned for a context which makes them significantly more accurate than all alternate cloud-based solutions. You can test the models within your browser as you are working on them.
Get in Touch
Picovoice is built by developers for developers. Your feedback is an essential part of the process. If you have any technical feedback and want to report a bug, you can create a GitHub issue. For commercial inquiries feel free to contact us directly.