ElevenLabs has introduced Projects, an AI based tool aimed at simplifying the generation and editing of long-form audio like audiobooks. It is based on the company’s research into long-form speech synthesis, audio conditioning, and parallelized audio generation.
Addressing Previous User Challenges
Before the introduction of Projects, users reported challenges like stability issues when producing extended content and difficulties in merging text fragments spoken by different voices. The platform’s previous limitations also made it challenging to regenerate specific audio sections and restricted users to certain text file formats.
Projects seeks to address these concerns by offering features such as:
- One-click generation of entire audiobooks.
- Assigning text fragments to specific speakers while maintaining context.
- Adjusting pause lengths for pacing.
- Selective regeneration of audio fragments without redoing entire sequences.
- Support for .epub, .pdf, .txt file formats, and URL-based project initiation.
Features and Compatibility
The tool provides a range of features, including full conversion capabilities, speaker assignment, segment regeneration, manual pause adjustments, chapter segmentation, and a save and resume function. It also supports importing files from various formats and URLs.
In terms of compatibility, Projects integrates with ElevenLabs’ existing tools like Speech Synthesis, VoiceLab, and Voice Library. Additionally, it works in conjunction with Professional Voice Cloning, Voice Library, and ElevenLabs’ multilingual model.