-
-
Save urodelagames/6ad8a429e73d114e64467988854e8eb0 to your computer and use it in GitHub Desktop.
This is the speech-to-text Flask app that receives requests from the Phonograph game I made for Godot Wild Jam #35.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from flask import Flask, request | |
import speech_recognition as sr | |
import uuid | |
import wave | |
app = Flask(__name__) | |
@app.route('/', methods = ['GET']) | |
def index(): | |
return "hello world" | |
@app.route('/stt_test', methods = ['GET']) | |
def stt_test(): | |
return get_text_from_speech() | |
@app.route('/stt', methods = ['GET']) | |
def get_stt(): | |
data = bytes(bytearray.fromhex(request.get_data(as_text=True))) | |
return get_text_from_speech(data) | |
def get_text_from_speech(data): | |
r = sr.Recognizer() | |
id = str(uuid.uuid4()) | |
wav_file_name = "{}.wav".format(id) | |
with wave.open(wav_file_name, "wb") as wav_file: | |
wav_file.setnchannels(2) | |
wav_file.setsampwidth(2) | |
wav_file.setframerate(44100) | |
wav_file.writeframesraw(data) | |
audio_file = sr.AudioFile(wav_file_name) | |
with audio_file as source: | |
audio = r.record(source) | |
text = r.recognize_google(audio) | |
# text = r.recognize_sphinx(audio) | |
return text | |
if __name__ == '__main__': | |
app.run(port = 5000) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment