In this guide, we will show you how to use Postman, an API collaboration tool, to extract Speech to Text & Conversational Action Items from an audio.
- Get Symbl Authentication 🔐
- Submit your Audio file 🎤
- Receive Speech to Text & Conversational Action Items 🎁
We are going to use the Async API to upload the audio file. After processing the request, we will get a Conversation ID, and will use this Conversation ID in the Conversation’s Message API & Insight API for receiving data.
Here’s our magical Postman link which will surface our API collection.
After clicking the run in postman button, please select Postman for Windows/Mac option only.
If you see "A collection Symbl APIs already exists", click Replace.
Before we can begin processing your file, you will need to retrieve your credentials. Your credentials consist of your
appSecret. You can find them on the home page of the platform.
- After you have clicked on the Postman link provided above. Click on Authentication folder on the left.
Click on Generate Token(Authenticate) option and you’ll be able to see the API. Inside the Body tab, you’ll see
Paste your credentials(from platform homepage), click Send, and you should see
accessToken(like in the image below) generated. This token is automatically copied to all other APIs in Postman. So, you don't need to copy this Token.
To upload your audio file, you have to use the Async Audio API. This API takes your audio file and processes it. After processing it, it gives you a Conversation ID as a unique ID for your audio file and a Job ID for tracking the audio processing job.
- Inside your Postman app, click on Async APIs and then click on Audio – Submit New Audio. This will open the Async Audio API.
Please click here to download an audio file if you don’t have one handy. This file
business_meeting.mp3is provided for ease of testing.
Once the audio file downloads, click on Headers and change the value of
Click on the Body section. Then click on Select File and choose the file
business_meeting.mp3or whichever file you wish to use. Click Send and in 30 or so seconds, you’ll receive the
Stuck? We would love to help you
Ping us at Developer Slack Forum and we will get back to you in few hours.
After you receive the
conversationId in the response, you can now use the GET Conversation’s Messages API to receive Speech to Text for it.
In Postman Collection (on the left hand side) select Conversation API, in the expanded view click on Get Messages and press Send. And you should be able to see Speech to Text data in API response. The
conversationId is automatically picked up from the Async Audio API response.
If you don’t see any results when you click send, give the system 1 minute to process and click on send again.
In the Conversation API tab in Postman, click on Get Action Items and press Send. This way you’ll be able to see the action items from the audio clip you uploaded. If you want to know more about action items and APIs like it, click here.
If you want to learn more check out Introduction to Conversation API.
If you want to try more APIs, please click on Get Topics, Get Questions, Get Entities, etc in the Conversation API tab in Postman.
🎉 Congratulations! 🎉 You now know how to get Speech to Text & Conversational Insights from an audio file.