AI Text to Speech
First, open the editor and find AI Speech in the left-side panel. After entering, type or paste your text into the “Enter text” box (up to 4000 characters).
Next, go to the “Current Voice” section and click to explore all available voices.
We offer a wide range of options from popular platforms such as Microsoft, Google, MiniMax, ElevenLabs, Fish Audio, Qwen, and ByteDance. You can use the search bar at the top to filter by name, voice characteristics, language, or model. Click on any avatar to preview the voice, and hover over it to use or favorite it.
After selecting your preferred voice, close the panel and return to the main screen. Click the settings icon next to the voice to adjust speed and pitch (some voices also support style settings). Once everything is set, click the Generate button at the bottom.
After the audio is generated, you can preview it, download it directly, or click “Save to Media” to use it in your current video project.
Voice Cloning
If you’d like to use your own voice, you can do so through the Voice Cloning feature.
Go to the Voice Cloning section and click “Clone”.
You can either record your voice directly or upload a file that contains clear speech. Supported formats include MP3, WAV, and MP4 (minimum 10 seconds, maximum 100MB).
Next, choose the model and language (it’s best to match your original voice), then enter a name for your voice and select an avatar. After that, click Generate to create your cloned voice.
Once the cloned voice is ready, simply hover over it and click Use to apply it in AI Speech for text-to-speech.
