Audio & Voice
VisionStory supports 88 languages, including English, Chinese, Spanish, Arabic, Portuguese, Russian, Japanese, Punjabi, German, French, Korean, Turkish, Tamil, Vietnamese, Hindi, Bengali, Urdu, Persian, Italian, Indonesian, Thai, Marathi, Telugu, Ukrainian, Malay, Romanian, Polish, Dutch, Gujarati, and Kannada.
VisionStory provides a library of 1,000+ voices, which you can filter by gender, age, and use case. If you don’t find a voice that fits your needs, you can create a custom AI voice clone by uploading or recording your own audio.
The limited voice options in certain languages are specifically fine-tuned for those languages. However, the underlying language support allows voices, such as those in English, to speak multiple languages, providing flexibility in voice selection.
Voice cloning allows you to create a custom AI voice that mimics a specific voice by uploading or recording audio. To clone a voice, ensure the audio is recorded clearly in a quiet environment for optimal results.
To use voice clone in video generation, you need to subscribe to the Pro plan or higher.
Voice cloning is freely supported in more than 32 languages. The list of supported languages is subject to change, so please check the voice cloning function for the most current options. Please note: althogh the cloning is free, to use the cloned voice in video needs subscription.
Preview audio allows you to generate the speech for your talking video before the final video creation. This feature helps you check the voice, pronunciation, and pauses to ensure they meet your expectations. You can make adjustments to the voice before generating the video. For all the subscribers, this feature is free to use, with a preview quota reset daily. If you reach the daily preview quota, you could purchase more quota using credits.
The stopwatch icon and +0.5s feature allow you to insert a 0.5-second pause in the generated voice. You can add multiple stopwatch icons consecutively to create longer pauses as needed in your video.
URL import allows you to import audio from a link by downloading and extracting the audio from the specified URL to use in video generation. Currently, it supports links from YouTube and TikTok. If you would like to see support for more sites, please contact us. Additionally, you can use the voice changer feature to modify the imported audio while keeping the original content.
The remove noise feature helps eliminate background noise from audio when you import or record it, ensuring clearer audio quality for your videos. This feature is free to all users.
The voice changer feature allows you to modify the voice in a speech, enabling you to create unique renditions of the audio while maintaining the original content. This feature is free to all users.
Emotion in the voice is conveyed through the text you provide. When you use different text, the text-to-speech (TTS) system naturally applies the appropriate emotion, so no additional control is needed.
When using the stopwatch feature, each stopwatch represents a 0.5-second pause, and you can use them consecutively to create longer pauses, up to a maximum of 3 seconds. However, avoid using more than two consecutive pauses within a single text segment, as this may cause the AI to produce unexpected sounds or artifacts.
