Speech-to-Speech (STS) allows you to convert spoken audio from one language into another, maintaining the tone and style of the original speaker. Follow the steps below to get started and make the most of this feature.
1. Getting Started
- Click Create New Project and select Speech-to-Speech.
- Enter a name for your project to help you stay organized.
2. Upload or Record Audio
You can either:
- Upload an audio file directly from your device, or
- Record audio using the built-in recording tools on the platform.
3. Choose Your Preferences
Before generating the translated audio:
- Select the source language (original language of the audio).
- Choose the target language (language for translation).
- Pick a voice from the available options.
- Confirm that you have the legal rights to use the original voice content.
- Click Generate to start the translation process.
4. Download the Output
Once the translation is complete:
- The platform will provide a downloadable version of the translated audio.
- Click Download to save it to your device.
Best Practices for Using STS
To ensure high-quality results, keep the following in mind:
- Use clear, noise-free audio.
- Avoid multiple people speaking at once.
- Make sure the source language is selected correctly before generating.
Audio File Requirements
- Supported file formats: .mp3, .wav, m4a ,aac
Credits and Limits
| Plan | Credits/Min | Total Minutes | Max Duration (Min) | Max file size (MB) |
| Free | 800 | 12 | 0.5 | 150MB |
| Student | 800 | 27 | 5 | 300MB |
| Pro | 800 | 562 | 15 | 750MB |
| Teams | 800 | 2755 | 45 | 750MB |
