# Install from ollama.com, or:
curl -fsSL https://ollama.com/install.sh | sh
 
# Pull a fast model
ollama pull qwen3:14b

git clone https://github.com/ggerganov/whisper.cpp.git
cd whisper.cpp
 
# Build
cmake -B build && cmake --build build --config Release
 
# Download a medium model (good balance of speed/accuracy)
bash models/download-ggml-model.sh medium

# Record a short test (requires ffmpeg)
ffmpeg -f dshow -i audio="Microphone" -t 5 test.wav
./build/bin/whisper-cli -m models/ggml-medium.bin -f test.wav

pip install kokoro

from kokoro import KPipeline
pipeline = KPipeline(lang_code='a')  # American English
for result in pipeline("Hello, this is your local AI assistant speaking."):
    with open('output.wav', 'wb') as f:
        f.write(result.audio)

import subprocess
import tempfile
import wave
import pyaudio
import requests
from kokoro import KPipeline
 
OLLAMA_URL = "http://localhost:11434/api/generate"
MODEL = "qwen3:14b"
WHISPER_BIN = "./whisper.cpp/build/bin/whisper-cli"
WHISPER_MODEL = "./whisper.cpp/models/ggml-medium.bin"
 
tts_pipeline = KPipeline(lang_code='a')
 
def record_audio(duration=5, sample_rate=16000):
    p = pyaudio.PyAudio()
    stream = p.open(format=pyaudio.paInt16,
                    channels=1,
                    rate=sample_rate,
                    input=True,
                    frames_per_buffer=1024)
    frames = []
    for _ in range(0, int(sample_rate / 1024 * duration)):
        data = stream.read(1024)
        frames.append(data)
    stream.close()
    p.terminate()
    
    with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as f:
        wf = wave.open(f, 'wb')
        wf.setnchannels(1)
        wf.setsampwidth(p.get_sample_size(pyaudio.paInt16))
        wf.setframerate(sample_rate)
        wf.writeframes(b''.join(frames))
        wf.close()
        return f.name
 
def transcribe(audio_file):
    result = subprocess.run(
        [WHISPER_BIN, '-m', WHISPER_MODEL, '-f', audio_file],
        capture_output=True, text=True
    )
    return result.stdout.strip()
 
def ask_llm(prompt):
    response = requests.post(OLLAMA_URL, json={
        "model": MODEL,
        "prompt": prompt,
        "stream": False
    })
    return response.json()["response"]
 
def speak(text):
    for result in tts_pipeline(text):
        with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as f:
            f.write(result.audio)
        subprocess.run(['ffplay', '-nodisp', '-autoexit', f.name])
 
# Main loop
print("Listening... (speak within 5 seconds)")
audio_file = record_audio(5)
print("Transcribing...")
text = transcribe(audio_file)
print(f"You said: {text}")
 
print("Thinking...")
response = ask_llm(text)
print(f"AI: {response}")
 
print("Speaking...")
speak(response)

pip install pyaudio requests
python voice_assistant.py