I have built an online text-to-speech platform based on the Microsoft Edge TTS engine. It's completely free, requires no registration, and is ready to use upon opening.
I previously offered a similar service, but had to suspend it due to server expiration and other issues.
Now, leveraging the powerful Workers technology from Cloudflare, this platform has been rebuilt and provides stable and reliable free service! As long as the usage isn't extremely high, it won't incur any costs, and therefore there's no need to shut it down, unless Microsoft strengthens its rate limiting measures and no longer offers free usage someday.
Completely Free: Built on Cloudflare Workers, leveraging their free tier. I don't need to pay for servers, and thus, there are no charges for users.
High-Quality Voice: Uses the Microsoft Edge TTS engine, resulting in natural and fluent speech that closely resembles human voice.
Multilingual Support: Supports multiple languages and a wide range of voice characters to meet your diverse needs.
Emotion Adjustment: Offers over 20 tone and emotion choices (such as anger, happiness, sadness, etc.) to make your voice more expressive. (Some characters may not support emotion adjustment.)
Easy to Use: No software installation required. Operate directly on the webpage for convenience and speed.
Customizable Parameters: Adjust parameters like speech rate, pitch, and volume to create personalized speech.
How to Use?
Just three simple steps to get the voice you want:
Access the Website: Click the link https://tts.pyvideotrans.com to access the online text-to-speech platform. You can directly enter text in the text box, or upload SRT subtitle files or TXT text files.
Select Language and Character: Accurately select the language corresponding to the text and choose your preferred voice character. You can click the preview button to listen to the different character voices.
Customize and Synthesize: Set parameters such as speech rate, pitch, volume, and tone/emotion, then click the "Execute" button. After the synthesis is complete, you can download the audio file or play it directly on the webpage.
Adding Silent Fragments: A Quick Tip
To make the speech more rhythmic, you can add silent fragments to the text.
Method: Add square brackets [] at the end of the line where you want to add silence, and enter the silence duration in milliseconds inside the brackets. For example, [500] indicates adding 500 milliseconds of silence after that line.
Note
Each line of text should not be too long, otherwise it may cause synthesis failure. Please keep each line concise.
Speech synthesis is performed line by line, and the addition of silent fragments takes effect between lines.