edgeTTS Voice Channel

What is it?

edgeTTS is a free text-to-speech service from Microsoft, built on the speech synthesis technology used in Edge browser. No registration, no API key, no payment required. It supports many languages worldwide, with at least 2 voice options per language.

Advantages:

• Completely free, no account needed
• No proxy or VPN required — works directly from anywhere
• Supports all languages
• Stable and reliable voice quality
• High concurrency support (default: 10 concurrent requests)

How to Use

Step 1: Select the Voice Channel

In the Voice Channel dropdown on the main interface, select edgeTTS.

Step 2: Select the Target Language

In the Target Language dropdown, choose your desired language (e.g., English, Japanese, Korean, etc.).

Step 3: Select a Voice

After selecting the target language, the Voice dropdown will automatically load all available voices for that language. Click the play button next to a voice name to preview it, then select the one you like.

Step 4: Start Dubbing

Once configured, click the dubbing button to begin. No additional setup is needed.

Advanced Settings

Adjusting Speed and Pitch

edgeTTS supports adjusting speech rate and pitch in Advanced Options:

• Speed: Positive values speed up, negative values slow down (e.g., +20% for 20% faster)
• Pitch: Positive values raise pitch, negative values lower it

Bypassing Proxy

If you use a system proxy and edgeTTS has connection issues, create an empty file named edgetts-noproxy.txt in the software's root directory. edgeTTS will bypass the proxy and connect directly.

Concurrency and Retries

Default concurrency is 10 with 3 retries. If you encounter rate-limiting timeouts, try reducing the concurrency.

Troubleshooting

Issue	Solution
"Connection refused" or timeout	Check your network connection; if using a proxy, try creating the edgetts-noproxy.txt file
"NoAudioReceived" error	Microsoft may be rate-limiting — wait a few minutes and retry
Some voices unavailable	Some voices may have been retired by Microsoft — try a different one
Audio quality not great	edgeTTS uses synthetic speech with fixed quality; for higher quality, consider AzureTTS or ElevenLabs