—
OpenMOSS
OpenMOSS is an AI-native company in —. Shown below: 7 models.
$200M
Listed valuation
- Listed models
- 7
- Listed papers
- 1
Figures and classifications reflect imported catalog records, not live company reporting.
Models
7
-
MOSS VL Realtime Gen 3 Multimodal
An 11B parameter vision language model built for continuous video streams. It perceives incoming frames and generates text in parallel, answers questions asked at any point in the stream, and can stay silent or revise e…
- Video analysis
- Images
- Videos
- Image analysis
- Visual analysis New
-
MOSS TTS v1.5 Gen 3 Multimodal
MOSS MOSS-TTS is OpenMOSS and MOSI.AI’s open-source speech and sound generation family for voice cloning, dialogue speech, voice design, real-time TTS, and sound effects.
-
MOSS Audio Gen 3 Multimodal
An open-source unified audio understanding model family from MOSI.AI, OpenMOSS, and the Shanghai Innovation Institute. It is built to handle speech, environmental sound, music, captioning, time-aware QA, and complex aud…
- Transcription
- Voice recognition
- Audio translation
- Music analysis
-
MOSS TTS Nano Gen 3 Multimodal
An open-source multilingual tiny speech generation model from MOSI.AI and OpenMOSS. With only 0.1B parameters, it is built for real-time TTS, can run directly on CPU without a GPU, and keeps deployment simple enough for…
- Text to speech
- Voice cloning
- Multilingual communication
-
MOSS TTS Local Transformer v1.5 Gen 4 Audio
A 5B-parameter text-to-speech model supporting 31 languages with zero-shot voice cloning, long-form speech generation, token-level duration control, Pinyin/IPA pronunciation control, code-switching, and 48 kHz stereo au…
- Text to speech
- Voice cloning
- Voiceovers
- Audiobooks
-
MOVA Gen 3 Video
Open source foundation model that jointly generates video and audio in one pass, achieving tightly synchronized lip movements and environment-aware sound effects.
- Videos
- Text to speech
- Music
- Animations
-
MOSS Transcribe Diarize Gen 4 Audio
An end to end multimodal large language model that jointly performs speech transcription, speaker diarization, and timestamp prediction. It projects multi speaker acoustic representations into the feature space of a pre…
- Transcription
- Podcast transcription
- Voice recognition
- Meeting transcription
In the catalogs
9
Repositories
- Embodied-Planner-R1 Embodied-Planner-R1: Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
- FDU-AI-PRML-2024Fall Fdu Ai Prml 2024Fall
- HalluQA Dataset and evaluation script for
- MOSS-Audio An open-source model for understanding speech, environmental sounds, and music through captioning, question a…
- MOSS-Audio-Tokenizer MOSS-Audio-Tokenizer is a Causal Transformer-based audio tokenizer built on the CAT architecture. Trained on…
- MOSS-Transcribe-Diarize MOSS-Transcribe-Diarize
- MOSS-VL MOSS-VL is the core multimodal model series within the OpenMOSS ecosystem, dedicated to visual understanding.
- Sparse-dLLM A training-free framework that accelerates diffusion language models through dynamic cache eviction and spars…
- SpeechGPT-2.0-preview GPT-4o-level, real-time spoken dialogue system.
Source rankings
Imported positions; not an independent quality score.
- Overall Rank#1269
- AI Native Rank#598