Academic Textbook Search
Browse and search public academic textbook PDF links.
open multi-modal foundation models and datasets for their creation; scaling laws, model evaluation; fully local, sovereign model deployment, personalized assistants and open local agentic systems
LAION-Audio-XL: A Web-Scale Corpus and Scaling Studies for Contrastive Language-Audio Pretraining
LAION-BVD: A 10-Million-Hour Open Video Dataset for Multimodal Pre-training
Browse and search public academic textbook PDF links.
Five languages, two voices, Best-of-4 / 2 / 1
Explore emotion‑driven voice samples across languages
Explore AI‑generated podcast conversations with two fixed voices
Compare podcast speech outputs with different timing settings
Explore AI‑generated multilingual podcast conversations
Explore a searchable catalogue of voice‑acting situations
Script analysis, annotation and performance taxonomies
Explore and compare synthetic voice samples across checkpoints
Explore and listen to 53 separated music stems with this web demo
Explore and listen to diverse singing voice samples
Generate multi‑speaker podcast dialogue continuations
Search expressive voices by acting direction and score
Compare synthetic speech emotions across models
Generate expressive voice audio with specific emotions
Generate expressive speech from text with optional voice reference
Generate expressive speech using emotion‑style voice adapters
Explore and compare AI video/audio model predictions on TikTok clips
Generate expressive speech from text with optional voice reference
Generate spoken audio from text with optional voice cues
Compare voice model checkpoints and listen to results
Listen to and compare synthetic voice samples by emotion and voice
Convert any speech to a chosen target voice
Listen to embedded voice‑acting captions online