Web Speech API
A native JavaScript speech interface provided by browsers, comprising two modules: SpeechRecognition for speech-to-text and SpeechSynthesis for text-to-speech. It enables basic voice interaction without third-party speech services.
Timeline (last 90 days)
The Bob project uses a four-layer architecture: a Web Speech API voice frontend, an AI Agent in n8n, an MCP protocol connection layer, and an ESP8266 hardware end.
The Web Speech API is a JavaScript interface natively provided by browsers, consisting of two parts: SpeechRecognition (speech-to-text) and SpeechSynthesis (text-to-speech).
The recognition quality of the Web Speech API depends on the browser implementation; mainstream browsers such as Chrome usually call cloud-based speech services behind the scenes, so it is not fully offline, and its robustness for non-English languages and noisy environments is limited.
TerraGemma synthesizes speech locally in the browser via a self-contained HTML/JS component that calls window.speechSynthesis (the Web Speech API), without invoking any external cloud-based TTS.
Modern browsers' Web Speech API provides a native speech recognition interface, and technologies such as WebGPU and ONNX Runtime Web allow lightweight neural network models to run directly in the browser.
All Facts (5)
The Bob project uses a four-layer architecture: a Web Speech API voice frontend, an AI Agent in n8n, an MCP protocol connection layer, and an ESP8266 hardware end.
50%UnverifiedThe Web Speech API is a JavaScript interface natively provided by browsers, consisting of two parts: SpeechRecognition (speech-to-text) and SpeechSynthesis (text-to-speech).
50%UnverifiedThe recognition quality of the Web Speech API depends on the browser implementation; mainstream browsers such as Chrome usually call cloud-based speech services behind the scenes, so it is not fully offline, and its robustness for non-English languages and noisy environments is limited.
50%UnverifiedTerraGemma synthesizes speech locally in the browser via a self-contained HTML/JS component that calls window.speechSynthesis (the Web Speech API), without invoking any external cloud-based TTS.
50%UnverifiedModern browsers' Web Speech API provides a native speech recognition interface, and technologies such as WebGPU and ONNX Runtime Web allow lightweight neural network models to run directly in the browser.
50%