Easily Convert Audio Files to Text with Speechmatics
Learn how to transcribe audio to text using Speechmatics API with simple commands. Follow step-by-step for accurate and fast transcription results.
File
The Speechmatics SaaS Portal How to Make Your First API Request
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: Hi there, I'm Paul and I'm Product Marketing Manager here at Speechmatics. In this short video you'll see just how easy it is to get from an audio file to an incredibly accurate text transcription using just a couple of commands. Before we begin, be aware that you're going to be running API commands through a command line interface, so please be sure you're up to speed with the basics first. To kick things off, you need an audio file to test with. You can use any media file that contains audio in a file format of AAC, AMR, FLAC, M4A, MP3, MP4, MPEG, OGG or WAV. But for this quick example, we're going to download the sample audio file you'll find on the Start Using API page. Make sure you save this to somewhere on your local machine that you have access to. Before we can make any API requests, you need an API key to verify your ability to access the Speechmatics API. For this example, I'm going to call this key Test. Be aware that this API key will only be displayed once for security reasons, so make sure you copy this and store it somewhere safe. You'll see that the command for submitting a media file for transcription has already been constructed for us, along with the API key we've just created. I'm on a Mac, so I'm going to switch tabs to get the command formatted correctly, and I'm going to click Copy to be able to copy this directly into the terminal. Now you need to switch to your terminal and navigate to the folder where the example file was saved from the website. Now you simply copy the API command directly in, which already has the correct API key and point to the example audio file. You'll see that quickly you'll get back an ID in the terminal. This is the ID of the transcription job, indicating that the API request was successful and the transcription is being processed. I'll come back to this soon, as we'll need to get the actual transcription content back. If you quickly head back to the portal, you can see that the second command is focused on getting the transcription back. Again, you need to copy this and paste it into the terminal command line. You'll see that we're missing the job ID that is required for this API request to run. Go back to where you received the job ID from the previous request and place it where it's needed in the GET request. Now let's run the GET request. And you'll see that we get back the transcription incredibly quickly, directly into the terminal. You can then copy and paste this into another application to edit or directly into a different workflow. So that was a quick introduction to making your first request with the Speechmatics API. If you have any questions at all, please reach out to us for help and let us know what you're building with the Speechmatics API.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript