Skip to content
Fan Zeng (Frank)
Back to resources

LibriTTS

LibriTTS restructures audiobook recordings and text from LibriSpeech for multi-speaker English synthesis.

Visit official source (opens in a new tab)

Research use

Use the established speaker and text splits to compare multi-speaker TTS systems.

Limitations

Audiobook narration can differ from conversational delivery, and the source overlaps with LibriSpeech.

License and access

Dataset license
CC BY 4.0 (opens in a new tab)
Access status
Direct access

Use the publisher’s resource page and check the terms for the files and version you choose.

Additional sources