Want your text to "speak" with natural, lifelike voices that rival real humans? Microsoft Edge's built-in "Read Aloud" feature can do just that! It supports dozens of languages and multiple voice styles, and the best part—it's completely free.
The open-source project edge-tts
, based on this feature, is also widely popular, and many free text-to-speech tools are developed using it. However, as user numbers grow, Microsoft has rate-limited voice synthesis requests. Now, even moderate usage can result in 403 errors, preventing further speech synthesis.
How to Avoid or Reduce 403 Errors?
Since this is an API service provided by Microsoft, not an open-source project, local deployment is not feasible. In any case, speech synthesis must connect to Microsoft's servers.
Deploy to Cloudflare: This can reduce the frequency of 403 errors but cannot completely prevent them.
- If you're interested, you can refer to this tutorial: https://pyvideotrans.com/edgettscf
Use Dynamic IP Proxies: Automatically switching IPs every few minutes can effectively avoid 403 errors. Stability depends on the quality of the dynamic IPs. If the dynamic IP reliability 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 are usually paid. Free proxies often have poor quality and cannot meet the requirements.
So, how to configure dynamic IP proxies, and which services are worth recommending?
Dynamic IPs cannot guarantee 100% availability; actual availability may only be around 85%-95%.
Here, I'll use Proxy302, which I have personally used, as an example. It provides foreign residential IPs, switching approximately every 5 minutes, and charges based on data usage ($1.5/GB).
Below are the detailed steps for registration and usage:
1. Register an Account
Visit 302AI to register an account. This account and its balance are shared with Proxy302. The reason for recommending registration through 302AI is that its minimum top-up amount is $5, whereas Proxy302's minimum is $20. For initial testing, it's advisable to top up a small amount to minimize risk.
Open this link to register: https://gpt302.saaslink.net/teRK8Y
Use your email to register and complete email verification.Top up your balance: Follow the illustration below to top up, with a minimum of $5.
2. Log in to Proxy302.com
After topping up, log in to https://dash.proxy302.com/login using the same account credentials.
Once logged in, you will see your balance.
3. Create a Dynamic IP Proxy Address
As shown above, click on Dynamic IP (Short-term) --> Pay by Traffic in the left navigation bar.
Then click Generate Universal Proxy --> Generate Universal Proxy, as shown below.
- After generation, you can see the new proxy address under Existing Proxies --> Purchased Proxies. Click the help button next to the address, set the country for the proxy IP, and copy the proxy address.
- As shown below, select
United States (US)
in the country field, click to generate a randomSession
, and copy the address at the bottom.
Important: Always click the
help
button to copy the proxy address each time you need it.
4. Apply the Proxy Address to Video Translation Software
First, you must upgrade the video translation software to version v3.50.
In the same directory as
sp.exe
for thepyVideoTrans
video translation software (or in the directory wheresp.py
is located if using source code deployment), create a plain text file namededgetts.txt
.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.
Billing is based on data usage. Roughly estimated, 1 RMB can synthesize about 3-5 hours of speech (retries due to errors will increase costs; actual expenses may vary, so test accordingly).