Gladia

How to build a Google Meet transcription bot with Python, React and Gladia API

Published on Jul 25, 2023

In today's fast-paced world, effective communication and collaboration are essential. Tools like Google Meet have revolutionized how we connect and conduct meetings remotely. However, it can be very challenging to keep track of all action items and key insights shared during long meetings.

import React, { useState, useEffect } from 'react'; import axios from 'axios'; const MeetingSummary = () => { const [summary, setSummary] = useState(''); useEffect(() => { axios.get('/api/meeting-summary') .then(response => { setSummary(response.data.summary); }) .catch(error => { console.error(error); }); }, []); return ( Meeting Summary {summary} ); }; export default MeetingSummary;

from selenium import webdriver import time import pyaudio import wave from google.cloud import storage from google.cloud import speech # Set up Selenium WebDriver driver = webdriver.Chrome() driver.get("https://meet.google.com/meeting-url") # Start recording the meeting audio def record_audio(): CHUNK = 1024 FORMAT = pyaudio.paInt16 CHANNELS = 1 RATE = 16000 RECORD_SECONDS = 600 # Adjust as per your meeting duration WAVE_OUTPUT_FILENAME = "meeting-recording.wav" audio = pyaudio.PyAudio() stream = audio.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK) frames = [] print("Recording started...") for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)): data = stream.read(CHUNK) frames.append(data) print("Recording finished.") stream.stop_stream() stream.close() audio.terminate() wave_file = wave.open(WAVE_OUTPUT_FILENAME, 'wb') wave_file.setnchannels(CHANNELS) wave_file.setsampwidth(audio.get_sample_size(FORMAT)) wave_file.setframerate(RATE) wave_file.writeframes(b''.join(frames)) wave_file.close() record_audio()

bucket = storage_client.bucket(bucket_name) file_path = "meeting-recording.wav" with open(file_path, 'rb') as f: # Open the file files = { # Sending a local audio file 'audio': (file_name, f, 'audio/'+file_extension[1:]), # Send it. Here it represents: (filename: string, file: BufferReader, fileMimeType: string) # You can also send an URL for your audio file. Make sure it's the direct link and publicly accessible. # 'audio_url': (None, 'http://files.gladia.io/example/audio-transcription/split_infinity.wav'), # Then you can pass any parameters you wants. Please see: https://docs.gladia.io/reference/pre-recorded 'toggle_diarization': (None, True), } print('- Sending request to Gladia API...'); response = requests.post('https://api.gladia.io/audio/text/audio-transcription/', headers=headers, files=files) if response.status_code == 200: print('- Request successful'); result = response.json() print(result) else: print('- Request failed'); print(response.json()) print('- End of work'); # open AI summary code here:

import React from 'react'; import axios from 'axios'; const MeetingRecorder = () => { const startRecording = async () => { try { await axios.post('/api/start-recording'); console.log('Recording started successfully!'); } catch (error) { console.error('Failed to start recording:', error); } }; const stopRecording = async () => { try { await axios.post('/api/stop-recording'); console.log('Recording stopped successfully!'); } catch (error) { console.error('Failed to stop recording:', error); } }; return ( ); }; export default MeetingRecorder;

from flask import Flask, jsonify app = Flask(__name__) @app.route('/api/meeting-summary', methods=['GET']) def get_meeting_summary(): # Retrieve the summary from the database or file summary = retrieve_summary_from_database() return jsonify(summary=summary) @app.route('/api/start-recording', methods=['POST']) def start_recording(): # Implement the code to start recording the meeting video return jsonify(message='Recording started') @app.route('/api/stop-recording', methods=['POST']) def stop_recording(): # Implement the code to stop recording the meeting video return jsonify(message='Recording stopped') if __name__ == '__main__': app.run()

STT API Benchmarks: How to measure accuracy, latency, and real-world Performance

Every product that depends on voice input lives or dies by its speech-to-text performance. Whether you're enriching CRM data from support calls, powering live captions in meetings, or triggering downstream actions via LLMs, transcription accuracy and speed aren’t just nice-to-haves. They’re essential to product functionality. If your STT engine stalls on latency or mistranscribes a customer’s request, it can break automations, derail user experiences, and create costly manual work downstream.