Generates high-quality Japanese speech from text with zero-shot voice cloning and emoji-based style controls; uses a flow-matching diffusion transformer over DACVAE continuous latents, includes a duration predictor and integrated SilentCipher watermarking. Japanese-only.
Generates music, sound effects, and general audio from text prompts using a medium-size Stable Audio 3 diffusion model — a balance of generation quality and inference cost suitable for prototyping, demo assets, and creative sound design workflows.
Provides a large-scale ASR corpus organized by normalized acoustic subsets for robustness training and evaluation. About 645,925 examples across 54 acoustic conditions (noise, echo, far-field, recording distortions) with many distortion/dropout/noise Parquet splits. Distributed as split Parquet files; license not specified on the dataset page.
Converts long-form multi-speaker audio/video into a compact, speaker-aware transcript with timestamps and anonymous speaker labels in one pass. Combines ASR and diarization in a single model, supports custom prompts/hotwords, and targets meetings, podcasts, interviews and long recordings.
Generates conversational speech and voice continuation from text and optional audio context, outputting Mimi audio codes. Built on a Sesame-style CSM with an 8B Llama-like backbone plus a smaller autoregressive audio decoder. Suited for local TTS inference and voice-cloning workflows.
Generates audio-driven avatar videos from text, images, or audio inputs with production-grade stability (accurate lip sync, identity consistency) and an 8-step distillation inference mode for faster serving; suitable for broadcasting, virtual hosts, animation, and multi-person scenarios.
Instruction-tuned, unified Gemma 4 12B multimodal model that accepts text, image and audio inputs and generates text outputs locally. Encoder-free design reduces multimodal latency and fits on consumer devices while offering long-context support and native thinking/system-prompt features.
A 12B unified, encoder-free multimodal model that directly ingests text, images and audio and returns text; supports very long contexts (up to 256K tokens), native function-calling/thinking modes, and small-model deployment for local or on-device use.
A human‑curated corpus of AI‑generated music with MP3s, cover art, exact generation prompts and a 32‑column metadata schema; uses a 70/30 quality vs. mainstream split and a three‑level taxonomy to support fine‑grained audio‑ML, prompt‑fidelity and recommendation research.
Large streaming-audio dataset for training and evaluating audio-LLMs and audio agents. About 2.28M clips grouped into multi-turn “streams” across six task subsets (ASR, speech translation, audio understanding, voice chat, proactive response, environment-aware); audio shipped as tar shards.
Generates multilingual text-to-speech with zero-shot voice cloning, token-level duration control, and inline pause markers. v1.5 improves multilingual fidelity (with language tags), cloning stability, and long-reference handling—suitable for research and production TTS pipelines.
Zero-shot TTS for expressive long-form monologue and multi-speaker dialogue, designed to preserve acoustic consistency, conversational coherence, and affective continuity. Trained on SwanData-Speech and using a 25 Hz VAE, pause-aware text conditioning, and a flow-matching DiT with DiffusionNFT fine-tuning.