Picovoice AI Playground

Try on-device voice AI and local LLMs in your web browser

Stop sending your data to remote servers and jeopardizing user experience in real-time applications with on-device Text-to-Speech, Speech-to-Text, Noise Suppression, Speaker Recognition, Speaker Diarization, Wake Word Detection, Speech-to-Intent, Voice Activity Detection, Speech-to-Index, and local LLMs.

picoLLM
LLM Quantization & Inference
End-to-end platform compresses any LLM without sacrificing accuracy and runs across Linux, macOS, Windows, Android, iOS, Chrome, Safari, Edge, Firefox, Raspberry Pi, supporting both CPU and GPU.
Start BuildingLearn More
Model used: Phi-2
Hello, Phi-2!
Hello! Start the demo to begin a conversation.

More from Picovoice

Power of LLM Quantization: Making Large Language Models Smaller and Efficient

Future of Generative AI: Small Language Models

Streaming Text-to-Speech in Python

Local LLM for Mobile: Run Llama 2 and Llama 3 on iOS

Local LLM for Desktop Applications: Run Llama 2 & Llama 3 in Python

Local LLM for Web Browsers: Run Llama with Javascript