news-04072024-135719

ElevenLabs, a startup known for its AI voice technology, has introduced a new tool called the AI Voice Isolator. This tool aims to help creators eliminate unwanted background noise from their content, such as films, podcasts, or YouTube videos. While this tool is free to use with some limitations, it faces competition from other creative solutions like Adobe that offer similar features.

The AI Voice Isolator works by processing uploaded content in the post-production stage to detect and remove unwanted noise, leaving behind clear dialogue. This tool is particularly useful for creators who may not have access to high-end equipment with ambient noise cancellation features. By using AI technology, ElevenLabs promises studio-quality speech extraction, as demonstrated by their head of design in a noise removal demo.

In real-world tests, the Voice Isolator successfully removed various background noises, such as door opening/closing and clapping, to extract clear speech. However, there were some sounds like wall banging and finger snapping that the tool struggled to eliminate. While it currently does not work on music vocals, it may be effective for certain songs.

Looking ahead, ElevenLabs is expected to make improvements to the Voice Isolator to enhance its performance further. The company has not disclosed much about the underlying models used in the tool or how user recordings contribute to model training. Users can opt out of personal data usage for training through a privacy policy form on the platform.

Currently, the Voice Isolator is available only through the ElevenLabs platform, with plans to offer API access in the future. Users can access a free plan with usage limits, allowing them to process up to 10 minutes of audio per month for free. For larger audio files, paid plans starting at $5/month are available.

Overall, the AI Voice Isolator from ElevenLabs presents a promising solution for creators looking to enhance the quality of their content by removing unwanted background noise. With ongoing improvements and potential API access in the pipeline, this tool has the potential to become a valuable asset for content creators seeking to deliver clear and professional audio output.