Sherpa-ONNX speech recognition
Sherpa-ONNX carries your voice from microphone to story.
Playworlds sends browser microphone audio to its voice gateway, where Silero detects speech and an int8 SenseVoice model running through Sherpa-ONNX transcribes supported languages without browser SpeechRecognition.
Play PlayworldsVoice or text · AI game master · Persistent saves
What it does
One focused layer in a multi-model game system.
- Model family
- SenseVoice via Sherpa-ONNX
- Job in Playworlds
- Server-side speech to text
- Languages configured
- Chinese, English, Cantonese, Japanese, Korean
Why the layer matters
Designed around the rhythm of play.
Server-side recognition
The same recognition path is used across supported browsers instead of depending on a browser-specific speech API.
Voice activity detection
Silero VAD identifies likely speech before recognition, helping the game separate a player turn from room noise.
Text-mode fallback
If microphone access or recognition is unavailable, the same adventure remains playable through text input.
Common questions
The short version
What does Sherpa-ONNX SenseVoice do in Playworlds?
Sherpa-ONNX SenseVoice provides speech recognition as one part of the Playworlds voice-adventure stack.
Is Playworlds built around a single AI model?
No. Playworlds separates narrative reasoning, speech recognition, text-to-speech, voice activity detection, and persistent game state into distinct layers.