I would like to be able to save the audio from the sample from Google’s cloud-based text-to-speed service. Is it possible to do this?

1

7 Answers

If you're going to do a lot of this, you should really use the API that they offer, but here's a quick step by step if you just want to download a single sample of Google's speech synthesis.

1. Go to the page in Google Chrome.
2. Open the Developer Tools (by pushing F12)
3. Go to the "Network" tab.
4. Enter the text you want to get audio of.
5. Click the "SPEAK IT" button.
6. Watch the "Network" tab populate with a couple of entries.
7. Right-click the entry that starts with data:audio/wav;base64, and click "Open in new tab".
8. In the new tab, right-click the audio player, and click "Save video as..."
9. Choose where you want to save the resulting .wav file.

Note: This will get you a (marginally) cleaner copy of the audio than recording the Stereo Mix from your sound card.

1

Edit: @3D1T0R 's answer is simpler and will most likely result in a higher quality file.

---

I would just use an audio recording program, such as Audacity, to record the "Stereo Mix" of your computer. You haven't specified an OS but assuming Windows:

• First go to the Sound applet in the Control Panel, go to the Recording tab, right-click Stereo Mix and select Enable. (If you don't see Stereo Mix, check Show disabled devices)

• Then download/open Audacity, and in the Recording Device dropdown box, select Stereo Mix. Then just hit Record, and anything you hear playing out of your speakers will be recorded to a sound file.

1

As predicted in this comment, the accepted answer is now broken. The basic approach still works though, except you have to save the proxy.json and then decode the base64-encoded audio:

cat proxy.json | jq '.audioContent' -r | base64 -d > your-audio.wav

I wrote a browser extension specifically for this purpose:

It uses the WebExtensions API to sniff HTTP responses and saves the wav audio when matched.

2

Here are the current steps

1. Go to
2. Open the Developer Tools (by F12)
3. Go to the "Network" tab.
4. Enter the text you want to get audio of.
5. Click the "SPEAK IT" button.
6. Click the “I’m not a robot” checkbox
7. Watch the "Network" tab populate with a couple of entries.
8. Right-click the entry that starts with proxy?url=
9. In the preview to right, click "copy" in the line for “audiocontent”
10. Save this as a text file (base64.txt). Remove the quotes (") from beginning and end This contains the base64 encoded audio
11. In Ubuntu, decode base64 to wav file with the following command:
12. cat base64.txt | base64 --decode > audio.mp3

basically the same way. Inspect json response, take audiocontent base64 and decode to wav.

To make it easier for you, I made a chrome extension named audiotts. Just click SPEAK IT button and waiting the audio player come in. You can download the audio using download menu of the audio player.

feel free to check that out 🤟

In this video is it very well explained in Hindi/Urdu that how you can Covert Google TTS and Download as mp3:

3

Your Answer

Sign up or log in

Sign up using Google Sign up using Facebook Sign up using Email and Password Submit

Post as a guest

Post Your Answer Discard

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy