As you may know, Microsoft Edge browser has a powerful "Read Aloud" feature. It supports dozens of languages, each offering a selection of different voices for pronunciation, delivering excellent results.
Based on this, a developer created a Python package called edge-tts. This package allows you to use Microsoft's TTS service in your programs, providing voiceovers for text or subtitles. For example, the video translation software pyVideoTrans integrates edge-tts, allowing users to directly select it as a voiceover option.
Unfortunately, the misuse of Microsoft TTS by users in China is quite prevalent, with some even using it for commercial voiceover sales. This has led Microsoft to restrict access from China. Frequent use may result in 403 errors, requiring an IP change or a stable connection to a foreign VPN to continue.
So, is it possible to set up a simple proxy service on a foreign server for personal use? This could improve stability and make the API compatible with OpenAI TTS, allowing direct use within the OpenAI SDK.
The answer is yes! I recently created a Docker image that makes it easy to pull and start this service on a server.
Once started, the service interface is fully compatible with OpenAI. Simply change the API address to http://your_server_ip:7899/v1 to seamlessly replace OpenAI TTS. Furthermore, it can be used directly within video translation software.
Here's a detailed guide on how to deploy and use it:
Step 1: Purchase and activate a US server
Step 2: Open port 7899 in the firewall
Step 3: Connect to the server via terminal
Step 4: Install Docker
Step 5: Pull the edge-tts-api image and start the API service
If you already have a server with Docker installed, you can skip to Step 5 to pull the image.
Step 1: Purchase and Activate a US Server
It's recommended to choose a server in the United States due to fewer or no restrictions. You can choose a Linux-based operating system; the following example uses Debian 12 and my personal provider, Yecaoyun. The reason for choosing it is simple: it's cheap and relatively stable, sufficient for a voiceover proxy.
If you already have a Linux server in Europe or America, you can skip this section and go directly to the next section. If not, please continue reading.
Then, choose any of the top four configurations; they should all be sufficient.
I personally use the configuration priced at 29 yuan/month.
Click the "Buy Now" button to enter the configuration page. Here, select Debian 12 as the server operating system, set the server password, and leave the rest as default.
After completing the payment, wait a few minutes for the server to be created and started successfully. Next, you need to configure the firewall and open port 7899. Only by opening this port will you be able to connect to the service for voiceovers.
Step 2: Open Port 7899 in the Firewall
If you plan to use a domain name and configure Nginx reverse proxy, you don't need to open the port. If you're not familiar with these, for simplicity, it's recommended to directly open the port.
The firewall settings interface varies depending on the server and panel. The following example uses the Yecaoyun panel I use; other panels can be used as a reference. If you know how to open a port, you can skip this section and go directly to the next section.
First, in "My Products & Services", click on the product you just activated to enter the product information and management page.
On this page, you can find the server's IP address and password.
Find "Firewall" under "Additional Tools" and click to open it.
Then open port 7899 as shown below:
Step 3: Connect to the Server via Terminal
If you already know how to connect to the terminal, or have Xshell or other SSH terminal, you can skip this step and go directly to the next section.
On the product information page, find Xterm.js Console and click it. Then follow the steps shown below:
When the above image appears, press Enter a few times.
When Login: is displayed, enter root after it, and then press Enter. 
Next, Password: will appear. At this point, you need to paste the password you copied (if you forgot it, you can find it on the product information page).
Note: Do not use Ctrl+V or right-click to paste, as this may cause extra spaces or line breaks to be entered, resulting in a password error.
Hold down the Shift key + Insert key to paste the password, to prevent the password from being correct but unable to log in, then press Enter.
The login is successful as shown below.
Step 4: Install Docker
If your server already has Docker installed or you know how to install it, you can skip this step.
Execute the following 5 commands in sequence. Make sure each command is executed successfully before executing the next command. These commands only apply to the Debian 12 series of servers.
After [root@xxxxxx~]#, right-click to paste the following command, and press Enter to execute after pasting.
Command 1: sudo apt update && sudo apt install -y apt-transport-https ca-certificates curl gnupg
Command 2: curl -fsSL https://download.docker.com/linux/debian/gpg | sudo gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg
Command 3: echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian $(lsb_release -cs) stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
Command 4: sudo apt update && sudo apt install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin
Command 5: Start the Docker service. sudo systemctl start docker && sudo systemctl enable docker && sudo usermod -aG docker $USER
This command can be pasted by right-clicking, and press Enter after pasting.
Step 5: Pull the edge-tts-api Image and Start the API Service
Enter the following command to automatically pull the image and start the service. Once started, you can use it in video translation software or other tools that support OpenAI TTS.
docker run -p 7899:7899 jianchang512/edge-tts-api:latest
Press Ctrl+C continuously to stop the service.
Note that this command will run in the foreground. If you close the terminal window, the service will stop.
You can use the following command instead to start the service in the background, and you can safely close the terminal after execution.
docker run -d -p 7899:7899 jianchang512/edge-tts-api:latest
If there are no errors, it means the startup was successful. You can open http://your_ip:7899/v1/audio/speech in your browser to verify. If a result similar to the one below appears, it means the startup was successful.
Using in Video Translation Software
Please update the software to v3.40 to use. Download the update from https://pyvideotrans.com/downpackage
Open the menu and go to TTS Settings -> OpenAI TTS. Change the interface address to http://your_ip:7899/v1
You can fill in SK arbitrarily, as long as it's not empty. In the role list, separate the roles you want to use with commas.
Available Voices/Roles
Below is a list of available roles. Please note that the text language and role must match.
Chinese voices:
zh-HK-HiuGaaiNeural
zh-HK-HiuMaanNeural
zh-HK-WanLungNeural
zh-CN-XiaoxiaoNeural
zh-CN-XiaoyiNeural
zh-CN-YunjianNeural
zh-CN-YunxiNeural
zh-CN-YunxiaNeural
zh-CN-YunyangNeural
zh-CN-liaoning-XiaobeiNeural
zh-TW-HsiaoChenNeural
zh-TW-YunJheNeural
zh-TW-HsiaoYuNeural
zh-CN-shaanxi-XiaoniNeural
English voices:
en-AU-NatashaNeural
en-AU-WilliamNeural
en-CA-ClaraNeural
en-CA-LiamNeural
en-HK-SamNeural
en-HK-YanNeural
en-IN-NeerjaExpressiveNeural
en-IN-NeerjaNeural
en-IN-PrabhatNeural
en-IE-ConnorNeural
en-IE-EmilyNeural
en-KE-AsiliaNeural
en-KE-ChilembaNeural
en-NZ-MitchellNeural
en-NZ-MollyNeural
en-NG-AbeoNeural
en-NG-EzinneNeural
en-PH-JamesNeural
en-PH-RosaNeural
en-SG-LunaNeural
en-SG-WayneNeural
en-ZA-LeahNeural
en-ZA-LukeNeural
en-TZ-ElimuNeural
en-TZ-ImaniNeural
en-GB-LibbyNeural
en-GB-MaisieNeural
en-GB-RyanNeural
en-GB-SoniaNeural
en-GB-ThomasNeural
en-US-AvaMultilingualNeural
en-US-AndrewMultilingualNeural
en-US-EmmaMultilingualNeural
en-US-BrianMultilingualNeural
en-US-AvaNeural
en-US-AndrewNeural
en-US-EmmaNeural
en-US-BrianNeural
en-US-AnaNeural
en-US-AriaNeural
en-US-ChristopherNeural
en-US-EricNeural
en-US-GuyNeural
en-US-JennyNeural
en-US-MichelleNeural
en-US-RogerNeural
en-US-SteffanNeural
Japanese voices:
ja-JP-KeitaNeural
ja-JP-NanamiNeural
Korean voices:
ko-KR-HyunsuNeural
ko-KR-InJoonNeural
ko-KR-SunHiNeural
French voices:
fr-BE-CharlineNeural
fr-BE-GerardNeural
fr-CA-ThierryNeural
fr-CA-AntoineNeural
fr-CA-JeanNeural
fr-CA-SylvieNeural
fr-FR-VivienneMultilingualNeural
fr-FR-RemyMultilingualNeural
fr-FR-DeniseNeural
fr-FR-EloiseNeural
fr-FR-HenriNeural
fr-CH-ArianeNeural
fr-CH-FabriceNeural
German voices:
de-AT-IngridNeural
de-AT-JonasNeural
de-DE-SeraphinaMultilingualNeural
de-DE-FlorianMultilingualNeural
de-DE-AmalaNeural
de-DE-ConradNeural
de-DE-KatjaNeural
de-DE-KillianNeural
de-CH-JanNeural
de-CH-LeniNeural
Spanish voices:
es-AR-ElenaNeural
es-AR-TomasNeural
es-BO-MarceloNeural
es-BO-SofiaNeural
es-CL-CatalinaNeural
es-CL-LorenzoNeural
es-ES-XimenaNeural
es-CO-GonzaloNeural
es-CO-SalomeNeural
es-CR-JuanNeural
es-CR-MariaNeural
es-CU-BelkysNeural
es-CU-ManuelNeural
es-DO-EmilioNeural
es-DO-RamonaNeural
es-EC-AndreaNeural
es-EC-LuisNeural
es-SV-LorenaNeural
es-SV-RodrigoNeural
es-GQ-JavierNeural
es-GQ-TeresaNeural
es-GT-AndresNeural
es-GT-MartaNeural
es-HN-CarlosNeural
es-HN-KarlaNeural
es-MX-DaliaNeural
es-MX-JorgeNeural
es-NI-FedericoNeural
es-NI-YolandaNeural
es-PA-MargaritaNeural
es-PA-RobertoNeural
es-PY-MarioNeural
es-PY-TaniaNeural
es-PE-AlexNeural
es-PE-CamilaNeural
es-PR-KarinaNeural
es-PR-VictorNeural
es-ES-AlvaroNeural
es-ES-ElviraNeural
es-US-AlonsoNeural
es-US-PalomaNeural
es-UY-MateoNeural
es-UY-ValentinaNeural
es-VE-PaolaNeural
es-VE-SebastianNeural
Arabic voices:
ar-DZ-AminaNeural
ar-DZ-IsmaelNeural
ar-BH-AliNeural
ar-BH-LailaNeural
ar-EG-SalmaNeural
ar-EG-ShakirNeural
ar-IQ-BasselNeural
ar-IQ-RanaNeural
ar-JO-SanaNeural
ar-JO-TaimNeural
ar-KW-FahedNeural
ar-KW-NouraNeural
ar-LB-LaylaNeural
ar-LB-RamiNeural
ar-LY-ImanNeural
ar-LY-OmarNeural
ar-MA-JamalNeural
ar-MA-MounaNeural
ar-OM-AbdullahNeural
ar-OM-AyshaNeural
ar-QA-AmalNeural
ar-QA-MoazNeural
ar-SA-HamedNeural
ar-SA-ZariyahNeural
ar-SY-AmanyNeural
ar-SY-LaithNeural
ar-TN-HediNeural
ar-TN-ReemNeural
ar-AE-FatimaNeural
ar-AE-HamdanNeural
ar-YE-MaryamNeural
ar-YE-SalehNeural
Bengali voices:
bn-BD-NabanitaNeural
bn-BD-PradeepNeural
bn-IN-BashkarNeural
bn-IN-TanishaaNeural
Czech voices
cs-CZ-AntoninNeural
cs-CZ-VlastaNeural
Dutch voices:
nl-BE-ArnaudNeural
nl-BE-DenaNeural
nl-NL-ColetteNeural
nl-NL-FennaNeural
nl-NL-MaartenNeural
Hebrew voices:
he-IL-AvriNeural
he-IL-HilaNeural
Hindi voices:
hi-IN-MadhurNeural
hi-IN-SwaraNeural
Hungarian voices:
hu-HU-NoemiNeural
hu-HU-TamasNeural
Indonesian voices:
id-ID-ArdiNeural
id-ID-GadisNeural
Italian voices:
it-IT-GiuseppeNeural
it-IT-DiegoNeural
it-IT-ElsaNeural
it-IT-IsabellaNeural
Kazakh voices:
kk-KZ-AigulNeural
kk-KZ-DauletNeural
Malay voices:
ms-MY-OsmanNeural
ms-MY-YasminNeural
Polish voices:
pl-PL-MarekNeural
pl-PL-ZofiaNeural
Portuguese voices:
pt-BR-ThalitaNeural
pt-BR-AntonioNeural
pt-BR-FranciscaNeural
pt-PT-DuarteNeural
pt-PT-RaquelNeural
Russian voices:
ru-RU-DmitryNeural
ru-RU-SvetlanaNeural
Swahili voices:
sw-KE-RafikiNeural
sw-KE-ZuriNeural
sw-TZ-DaudiNeural
sw-TZ-RehemaNeural
Thai voices:
th-TH-NiwatNeural
th-TH-PremwadeeNeural
Turkish voices:
tr-TR-AhmetNeural
tr-TR-EmelNeural
Ukrainian voices:
uk-UA-OstapNeural
uk-UA-PolinaNeural
Vietnamese voices:
vi-VN-HoaiMyNeural
vi-VN-NamMinhNeuralUsing in OpenAI SDK
You need to install the openai library pip install openai
from openai import OpenAI
client = OpenAI(api_key='12314', base_url='http://your_ip:7899/v1')
with client.audio.speech.with_streaming_response.create(
model='tts-1',
voice='zh-CN-YunxiNeural',
input='Hello, dear friends',
speed=1.0
) as response:
with open('./test.mp3', 'wb') as f:
for chunk in response.iter_bytes():
f.write(chunk)Directly using requests to call the API
import requests
res=requests.post('http://your_ip:7899/v1',data={"voice":"zh-CN-YunxiNeural",
"input":"Hello, dear friends",
speed=1.0 })
with open('./test.mp3', 'wb') as f:
f.write(res.content)