Getting started¶
Requirements¶
- Node.js 20 or newer
- For a real offline setup: whisper.cpp, Ollama and Piper — see setup.md. You can develop and test with the mock engines without installing anything.
Install¶
The loop¶
VoicePipeline runs audio → text → LLM → text → audio and keeps conversation
history so a whole spoken turn is one call:
import { VoicePipeline, WhisperCppStt, OllamaLlm, PiperTts } from 'whispa';
const pipeline = new VoicePipeline({
stt: new WhisperCppStt({ model: 'models/ggml-base.en.bin' }),
llm: new OllamaLlm({ model: 'llama3.2' }),
tts: new PiperTts({ model: 'voices/en_US-amy-medium.onnx' }),
systemPrompt: 'You are a concise voice assistant.',
maxHistory: 20,
});
const { transcript, reply, audio } = await pipeline.turn('recording.wav');
Individual steps¶
const text = await pipeline.listen('recording.wav'); // STT
const reply = await pipeline.respond(text); // LLM (updates history)
const wav = await pipeline.speak(reply); // TTS
Develop without native tools¶
import { VoicePipeline, MockStt, EchoLlm, MockTts } from 'whispa';
const p = new VoicePipeline({ stt: new MockStt('hi'), llm: new EchoLlm(), tts: new MockTts() });