Published On Feb 27, 2024
Real-time call transcription is great for increasing accessibility and is widely applicable across different industries like customer support and call center analysis.
In this video, we'll build a Flask application in Python to transcribe phone calls in real time with AssemblyAI, Twilio, and ngrok.
Relevant links:
1. Get an AssemblyAI API Key: https://www.assemblyai.com/dashboard/...
2. Sign up for Twilio: https://login.twilio.com/signup
3. Sign up for Ngrok: https://dashboard.ngrok.com/signup
4. GitHub repo: https://github.com/AssemblyAI-Example...
5. Blog post: https://www.assemblyai.com/blog/trans...
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬
🖥️ Website: https://www.assemblyai.com/discover/?...
🐦 Twitter: / assemblyai
🦾 Discord: / discord
▶️ Subscribe: https://www.youtube.com/c/AssemblyAI?...
🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 Demo
00:25 How it works
01:34 Getting started
01:45 Step 1: Set up credentials and environment
04:16 Step 2: Create the Flask application
06:26 Step 3: Define the root endpoint
09:04 Step 4: Get a Twilio number and open an ngrok tunnel
11:18 Step 5: Set up a WebSocket to receive speech
15:15 Step 6: Define a real-time transcriber
21:34 Step 7: Add real-time transcription to the WebSocket
25:55 Step 8: Automatically set the Twilio WebHook and ngrok tunnel
31:20 Graph ML - applications and results
#MachineLearning #DeepLearning