- 81
- 205 025
Picovoice
Canada
Приєднався 20 тра 2018
On-device voice AI and local LLM - powered by deep learning
Voice Assistant in Node.js using on-device LLM, STT, TTS and Wake Word tech
Demo of an on-device LLM-powered voice assistant running a 2022 MacBook Air M2 w/ 8GB memory
Microsoft Phi-2 quantized by picoLLM Compression: picovoice.ai/picollm/compression/
picoLLM Inference: picovoice.ai/picollm/inference/
Porcupine Wake Word: picovoice.ai/platform/porcupine/
Cheetah Streaming Speech-to-Text: picovoice.ai/platform/cheetah/
Orca Streaming Text-to-Speech: picovoice.ai/platform/orca/
Code: github.com/Picovoice/pico-cookbook/blob/main/recipes/llm-voice-assistant/nodejs/
Start Free: console.picovoice.ai/
#largelanguagemodels #llms #voiceai #voiceassistant #aiagents #artificialintelligence #machinelearning
Microsoft Phi-2 quantized by picoLLM Compression: picovoice.ai/picollm/compression/
picoLLM Inference: picovoice.ai/picollm/inference/
Porcupine Wake Word: picovoice.ai/platform/porcupine/
Cheetah Streaming Speech-to-Text: picovoice.ai/platform/cheetah/
Orca Streaming Text-to-Speech: picovoice.ai/platform/orca/
Code: github.com/Picovoice/pico-cookbook/blob/main/recipes/llm-voice-assistant/nodejs/
Start Free: console.picovoice.ai/
#largelanguagemodels #llms #voiceai #voiceassistant #aiagents #artificialintelligence #machinelearning
Переглядів: 228
Відео
Low latency voice to text transcription in real time
Переглядів 206Місяць тому
Discover how to transcribe speech to text in real-time using the Picovoice Cheetah Streaming Speech-to-Text Node.js SDK! Cheetah's ability to process voice data locally in real time makes it ideal for real-time applications whether you're broadcasting, adding transcription to meeting applications, or building AI agents. Resources: Overview: picovoice.ai/platform/cheetah/ Quick Start Guide: pico...
How to run Llama locally using Python
Переглядів 128Місяць тому
Discover how to run Llama 2 and Llama 3 models locally on your desktop using Picovoice’s picoLLM Inference Engine Python SDK and compressed Llama Models. This tutorial walks you through setting up the environment, running the models, and exploring the capabilities of LLMs without relying on cloud infrastructure. Resources: Overview: picovoice.ai/platform/picollm/ Quick Start Guide: picovoice.ai...
Transcribe streaming audio within web browsers
Переглядів 47Місяць тому
Discover how to add real-time transcription to your JavaScript applications using Picovoice's Cheetah Streaming Speech-to-Text engine. This tutorial guides you through setting up the project, initializing Cheetah, and transcribing speech-to-text on-device to ensure privacy and performance. Resources: Overview: picovoice.ai/platform/cheetah/ Quick Start Guide: picovoice.ai/docs/quick-start/cheet...
Speaker Diarization for Web-based Applications that run across Chrome, Safari, Firefox and Edge
Переглядів 47Місяць тому
Learn how to integrate speaker diarization into your web applications using Picovoice's Falcon Speaker Diarization Web SDK. This tutorial covers the process of identifying "who spoke when" in audio streams, making it ideal for multi-speaker environments. Resources: Overview: picovoice.ai/platform/falcon/ Quick Start Guide: picovoice.ai/docs/quick-start/falcon-web/ API Reference: picovoice.ai/do...
Convert voice to text using Javascript
Переглядів 79Місяць тому
Learn how to add cloud API transcription accuracy to your web applications without sacrificing privacy using Picovoice's Leopard Speech-to-Text Web SDK. This tutorial explains how to set up and use on-device speech recognition, ensuring privacy and real-time performance. Resources: Overview: picovoice.ai/platform/leopard/ Quick Start Guide: picovoice.ai/docs/quick-start/leopard-web/ API Referen...
Speaker Recognition Across Chrome, Safari, Firefox, and Edge
Переглядів 41Місяць тому
Implement Speaker Recognition for Web Applications Using JavaScript Learn how to add speaker recognition to your web applications using Picovoice's Eagle Speaker Recognition Web SDK. This tutorial guides you through setting up speaker enrollment and recognition, allowing your application to identify and verify speakers in real time. Resources: Overview: picovoice.ai/platform/eagle/ Quick Start ...
Real-time Deep Learning-powered Noise Suppression for Web Applications
Переглядів 49Місяць тому
AI-powered Noise Cancellation engine, Koala Noise Suppression removes background noises, and voices from online meetings and voice chats, enhancing speech quality and intelligibility in real time, while maintaining user privacy. In this tutorial, we show how to add noise suppression to your web applications using Picovoice's Koala Noise Suppression Web SDK. Resources: Overview: picovoice.ai/pla...
Detect Speech and Silence in Conversations using Cobra Voice Activity Detection Web SDK
Переглядів 77Місяць тому
Learn how to implement real-time voice activity detection (VAD) in your JavaScript applications using Picovoice's Cobra VAD engine. This tutorial covers setting up the project, initializing the Cobra engine, and detecting voice activity in real-time while keeping all processing on-device for privacy and low latency. Resources: Overview: picovoice.ai/platform/cobra/ Quick Start Guide: picovoice....
Adding Voice to Web Applications: Convert Text to Speech in JavaScript
Переглядів 882 місяці тому
Learn how to convert text into speech within your JavaScript applications across web browsers using Picovoice's Orca Text-to-Speech Web SDK. This guide covers the installation, model setup, and implementation of text-to-speech in modern browsers. Resources: Overview: picovoice.ai/platform/orca/ Quick Start Guide: picovoice.ai/docs/quick-start/orca-web/ API Reference: picovoice.ai/docs/api/orca-...
Building a hands-free voice AI agent for web with ReactJS
Переглядів 1172 місяці тому
Learn how to integrate wake word detection into your React.js voice AI agents to create hands-free experiences using Porcupine Wake Word. This tutorial covers the setup process, training custom wake word models, and deploying them in a React environment for efficient, low-latency voice activation. Resources: Overview: picovoice.ai/platform/porcupine/ Quick Start Guide: picovoice.ai/docs/quick-s...
Speaker Diarization: How to detect different speakers in an audio recording
Переглядів 2982 місяці тому
Learn how to implement speaker diarization in Python, identifying "who spoke when" in audio streams. This tutorial covers setup, speaker enrollment, and accurate identification using Falcon Speaker Diarization Python SDK. Don't forget to check out the tutorial to see other Python-based speaker diarization frameworks - pyannote, NVIDIA Nemo, and Simple Diarizer - as well: picovoice.ai/blog/speak...
Convert Speech to Text locally using Python across Linux, macOS, Windows, and Raspberry Pi
Переглядів 822 місяці тому
Learn how to convert speech to text using Picovoice's on-device Speech-to-Text engine Leopard's Python SDK. Leopard Speech-to-Text performs speech recognition locally on the device, keeping your voice data private (i.e. GDPR and HIPAA compliant by design). The SDK runs on Linux, macOS, Windows, and Raspberry Pi. On-device Speech-to-Text: picovoice.ai/platform/leopard/ Tutorial: picovoice.ai/blo...
How to generate srt files and add subtitles to videos using Python
Переглядів 8402 місяці тому
This tutorial shows how to add subtitles to any video using the Picovoice Leopard Speech-to-Text Python SDK. On-device Speech-to-Text: picovoice.ai/platform/leopard/ Tutorial: picovoice.ai/blog/speech-to-text-with-reactjs/ Demo: github.com/Picovoice/leopard/tree/master/demo/python-subtitle #speechtotext #pythonprogramming #python #pythontutorial #voiceai #transcription #deeplearning
Real-time Speaker Recognition and Identification in Python
Переглядів 7472 місяці тому
Learn to add real-time speaker identification to your Python app using Picovoice's Eagle Speaker Recognition Python SDK. This tutorial covers setting up the Eagle SDK, enrolling speakers, and recognizing speakers in real time. Resources: Eagle Speaker Recognition: picovoice.ai/platform/eagle/ Eagle Speaker Recognition Quick Start: picovoice.ai/docs/quick-start/eagle-python/ Eagle Speaker Recogn...
Record Audio from Web Browser: Web Audio API & MediaStream API
Переглядів 3063 місяці тому
Record Audio from Web Browser: Web Audio API & MediaStream API
Add Speaker Diarization to OpenAI's Whisper Speech to Text
Переглядів 1,1 тис.3 місяці тому
Add Speaker Diarization to OpenAI's Whisper Speech to Text
Enhance Speech by Suppressing Background Noise in real time using Python
Переглядів 1563 місяці тому
Enhance Speech by Suppressing Background Noise in real time using Python
How to Detect Voice Activity in Real Time using Python
Переглядів 5143 місяці тому
How to Detect Voice Activity in Real Time using Python
On-device Text-to-Speech in Python to build real-time AI agents with low latency
Переглядів 1653 місяці тому
On-device Text-to-Speech in Python to build real-time AI agents with low latency
AI powered Audio Search Engine : Voice Search for YouTube
Переглядів 653 місяці тому
AI powered Audio Search Engine : Voice Search for UA-cam
Build your own voice assistant with end-to-end recognition using Python:
Переглядів 1193 місяці тому
Build your own voice assistant with end-to-end recognition using Python:
Computer! Tea, Earl Grey, Hot: On-device Voice AI Agent on NodeJS
Переглядів 683 місяці тому
Computer! Tea, Earl Grey, Hot: On-device Voice AI Agent on NodeJS
Build your own Voice Assistant with End-to-End Voice Recognition using Python
Переглядів 2503 місяці тому
Build your own Voice Assistant with End-to-End Voice Recognition using Python
Add custom wake words to your application using Python
Переглядів 2413 місяці тому
Add custom wake words to your application using Python
Fast Real-time Speech Recognition with zero latency using Python
Переглядів 3834 місяці тому
Fast Real-time Speech Recognition with zero latency using Python
How to Run Llama Locally on Mac using Node.js and picoLLM Inference
Переглядів 2034 місяці тому
How to Run Llama Locally on Mac using Node.js and picoLLM Inference