Want to make your text "speak" in a natural, realistic, and human-like voice? Microsoft Edge browser's built-in "Read Aloud" feature can do just that! It supports dozens of languages and multiple voices, and the key is that it's completely free.

The open-source project edge-tts, based on this feature, is also very popular, and many free text-to-speech tools are developed based on it. However, as the number of users increases, Microsoft has limited the rate of dubbing requests. Now, even with slightly larger usage, you will encounter a 403 error, preventing you from continuing to synthesize speech.

How to Avoid or Reduce 403 Errors?

Since this is a Microsoft-provided API service, not an open-source project, local deployment is not feasible. In any case, speech synthesis must connect to Microsoft's servers.

1. Deploy to Cloudflare: Can reduce the frequency of 403 errors, but cannot completely avoid them.

   • If you are interested in this, you can refer to this tutorial: https://pyvideotrans.com/edgettscf

2. Use Dynamic IP Proxy: Automatically change the IP address every few minutes, which can effectively avoid 403 errors. Stability depends on the quality of the dynamic IP. If the reliability of the dynamic IP is 97%, then the availability of edge-tts can also reach 97%.

   • This seems to be the best solution currently. Of course, high-quality dynamic IP proxy services usually require payment. Free proxies are often of poor quality and cannot meet the demand.

So, how do you configure a dynamic IP proxy, and which services are worth recommending?

Dynamic IPs cannot guarantee 100% availability; actual availability may only be between 85% and 95%.

Here, I'll use Proxy302, which I have personally used, as an example. It provides foreign residential IPs, switches approximately every 5 minutes, and charges based on traffic (1.5 USD/GB).

Below are the detailed steps for opening and using:

I. Register an Account

1. Visit 302AI to register an account. The account and balance are shared with Proxy302. The reason for recommending registration from 302AI is that its minimum top-up amount is 5 USD, while Proxy302's minimum top-up amount is 20 USD. For the first try, it is recommended to top up a small amount first to reduce risk.

2. Open this link to register: https://gpt302.saaslink.net/teRK8Y Register an account using your email address and complete email verification.

3. Recharge your balance: Recharge as shown in the figure below, with a minimum recharge of 5 USD.

II. Log in to Proxy302.com

After recharging, log in to https://dash.proxy302.com/login using the same account and password.

After logging in, you can see the balance.

III. Create a Dynamic IP Proxy Address

1. Click on Dynamic IP (Short-term) --> Pay-as-you-go on the left navigation bar as shown above.

2. Then click General Proxy Generation --> Generate General Proxy in sequence, as shown below.

3. After generation, you can see the newly generated proxy address in Existing Proxy --> Purchased Proxy below. Click the help button behind the address to set the country of the proxy IP and copy the proxy address.

4. As shown in the figure below, select United States (US) in the country, click to generate a random Session, and copy the address at the bottom.

Important Note: Be sure to click the help button to copy the proxy address each time you need to copy it.

IV. Apply the Proxy Address to Video Translation Software

You must first upgrade the video translation software to version v3.50.

1. In the same directory as the pyVideoTrans video translation software's sp.exe (or in the sp.py directory if it is a source code deployment), create a plain text file named edgetts.txt.

2. Paste the proxy address copied in the previous step into the edgetts.txt file and save it, as shown below.

Now, you can try using edge-tts for speech synthesis.

Based on traffic billing, it is roughly estimated that 1 RMB can synthesize 3-5 hours of speech (retries due to errors will increase the cost, please test the actual cost yourself, this is for reference only).