I've built an online speech synthesis platform based on the Microsoft Edge TTS engine. It's completely free, requires no registration, and is ready to use right away.
I previously offered a similar service, but it had to be suspended due to server expiration and other reasons.
Now, thanks to the powerful Workers technology from the "Network Bodhisattva" (a playful term for helpful technology providers), I've rebuilt this platform to provide stable and reliable free service! As long as usage isn't extremely high, there won't be any costs, so there's no need to shut it down unless Microsoft strengthens its rate-limiting measures and stops providing free usage one day.
Completely Free: Built on Cloudflare Workers, enjoy the free tier. I don't need to spend money on servers, so there's naturally no need to charge.
High-Quality Voice: Uses the Microsoft Edge TTS engine, with natural and smooth voice output that closely resembles human pronunciation.
Multi-Language Support: Supports multiple languages and a wide selection of roles to meet your diverse needs.
Emotional Adjustment: Provides over 20 emotional tone options (such as angry, happy, sad, etc.) to make your voice more expressive. (Some roles may not support emotional adjustment.)
Easy to Use: No need to install any software, operate directly on the webpage for convenience and speed.
Customizable Parameters: Adjust parameters such as speech rate, pitch, and volume to create personalized speech.
How to Use?
Just three simple steps to get the voice you want:
Visit the Website: Click the link https://tts.pyvideotrans.com to enter the online speech synthesis platform. You can directly enter text in the text box, or upload an SRT subtitle file or TXT text file.
Select Language and Role: Accurately select the language corresponding to the text, and choose your favorite voice-over role. You can click the "Listen" button to preview the sound of different roles.
Customize and Synthesize: Set parameters such as speech rate, pitch, volume, and emotional tone, then click the "Execute" button. After the synthesis is complete, you can download the audio file or play it directly on the webpage.
Tip for Adding Silent Segments
To make the speech more rhythmic, you can add silent segments to the text.
Method: Add English brackets [] at the end of the line where you want to add silence, and fill in the duration of the silence (in milliseconds) inside the brackets. For example, [500] means adding 500 milliseconds of silence after the end of 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 segments also takes effect between lines.