Agent Zero AI framework
stt wip
evrardtf5e790a35b65
diff --git a/main.py b/main.pyindex 3b7a32b72..235f4bcb3 100644--- a/main.py+++ b/main.py@@ -1,4 +1,4 @@-import threading, time, models, os, sys, argparse, asyncio+import threading, time, models, stt, os, sys, argparse, asynciofrom ansio import application_keypad, mouse_input, raw_inputfrom ansio.input import InputEvent, get_input_eventfrom agent import Agent, AgentConfigdiff --git a/stt.py b/stt.pynew file mode 100644index 000000000..b7761bd42--- /dev/null+++ b/stt.py@@ -0,0 +1,65 @@+import os+from dotenv import load_dotenv+from groq import Groq+import pyaudio+import wave++load_dotenv() # take environment variables from .env.++# Utility function to get API keys from environment variables+def get_api_key(service):+ return os.getenv(f"API_KEY_{service.upper()}") or os.getenv(f"{service.upper()}_API_KEY")++def record():+ client = Groq(+ api_key=get_api_key("groq")+ )++ CHUNK = 1024+ FORMAT = pyaudio.paInt16+ CHANNELS = 2+ RATE = 44100+ RECORD_SECONDS = 10+ WAVE_OUTPUT_FILENAME = "output.wav"++ p = pyaudio.PyAudio()++ stream = p.open(format=FORMAT,+ channels=CHANNELS,+ rate=RATE,+ input=True,+ frames_per_buffer=CHUNK)++ print("* recording")++ frames = []++ for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):+ data = stream.read(CHUNK)+ frames.append(data)++ print("* done recording")++ stream.stop_stream()+ stream.close()+ p.terminate()++ wf = wave.open(WAVE_OUTPUT_FILENAME, 'wb')+ wf.setnchannels(CHANNELS)+ wf.setsampwidth(p.get_sample_size(FORMAT))+ wf.setframerate(RATE)+ wf.writeframes(b''.join(frames))+ wf.close()++ filename = os.path.dirname(__file__) + "" + WAVE_OUTPUT_FILENAME++ with open(filename, "rb") as file:+ transcription = client.audio.transcriptions.create(+ file=(filename, file.read()),+ model="whisper-large-v3",+ prompt="Human talking to personnal ia agent", # Optional+ response_format="json", # Optional+ language="en", # Optional+ temperature=0.0 # Optional+ )+ print(transcription.text)\ No newline at end of file