An open full-duplex voice model family that hears your tone and speaks with one. Adventists AI · Apache-2.0 · Recommended: Tag · Flash · Try it online · GitHub
Alternatives to Sophon-Realtime-v1
114 open-weight models that do the same job as Sophon-Realtime-v1, ranked by how close they are in task and size, then by popularity and how recent they are. Licence and VRAM are shown for each.
SenseNova-Vision is a unified multimodal model for computer vision. It reformulates heterogeneous visual perception tasks as text generation, image generation, or mixed text-image generation, instead of relying on task-specific heads, decoders, or loss functions for each individual task.
7BCC BY-NC 4.0627 117Jun 2026- Same category
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions. It introduces Dual-Resolution Speech Representations (an efficient 5Hz shared backbone + a 25Hz refined head) to cut compute while keeping high speech quality, and Core-Cocktail training to preserve…
9.5B256K ctx Apache 2.02.1K 194Dec 2025- Same category
- Commercial use OK
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3n models are designed for efficient execution on low-resource devices.
7.8B32K ctx Gemma Terms of Use8.7K 943Jun 2025- Same category
Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs.
31.7BA3B64K ctx Apache 2.04.3K 264Sept 2025- Same category
- Commercial use OK
We present BAGEL, an open‑source multimodal foundation model with 7B active parameters (14B total) trained on large‑scale interleaved multimodal data.
14.7B32K ctx Apache 2.08.8K 1.2KMay 2025- Same category
- Commercial use OK
Ultravox is a multimodal Speech LLM built around a pretrained Llama3.2-1B-Instruct and whisper-large-v3-turbo backbone.
683MMIT17.7K 96Feb 2025- Same category
- Commercial use OK
Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.
7B16K ctx MIT17.8K 3.7KJan 2025- Same category
- Commercial use OK
Ming-flash-omni Preview, an upgraded version of Ming-Omni, built upon a sparser Mixture-of-Experts (MoE) variant of Ling-Flash-2.0 with 100B total parameters, of which only 6B are active per token.
104BA7.6B32K ctx MIT2.8K 71Oct 2025- Same category
- Commercial use OK
- [2026.04.30] Release the preview version of the 8-step inference model SenseNova-U1-8B-MoT-8step-preview. In most cases, the image generation quality of this model closely matches that of the base model (see comparison and existing issues).
17.6B256K ctx Apache 2.0710 295Apr 2026- Same category
- Commercial use OK
We develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal inductive bias beyond the language paradigm.
74.3B128K ctx MIT770 224Mar 2026- Same category
- Commercial use OK
MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
5.2B40K ctx Apache 2.0657 42Apr 2026- Same category
- Commercial use OK
RxBrain (Hy-Embodied-RxBrain-1.0) is a unified multimodal foundation model for embodied cognition — a single model that couples language reasoning with visual imagination to deliver three core capabilities:
6.2B256K ctx Apache 2.0311 54Jul 2026- Same category
- Commercial use OK
We introduce MOVA (MOSS Video and Audio), a foundation model designed to break the "silent era" of open-source video generation. Unlike cascaded pipelines that generate sound as an afterthought, MOVA synthesizes video and audio simultaneously for perfect alignment.
?BApache 2.0883 134Jan 2026- Same category
- Commercial use OK
MOSS-Music is an open-source music understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
9.1B40K ctx Apache 2.0460 45Apr 2026- Same category
- Commercial use OK
Step-Audio 2 is an end-to-end multi-modal large language model designed for industry-strength audio understanding and speech conversation, presented in the paper Step-Audio 2 Technical Report.
8.3B16K ctx Apache 2.02.5K 272Aug 2025- Same category
- Commercial use OK
Step-Audio R1.1 (Realtime) is a major upgrade to Step-Audio-R1, designed for interactive spoken dialogue with both real-time responsiveness and strong reasoning capability.
33.5B64K ctx Apache 2.0954 193Jan 2026- Same category
- Commercial use OK
Lance is a 3B native unified multimodal model that supports image and video understanding, generation, and editing within a single framework.
?BApache 2.0381 1.1KMay 2026- Same category
- Commercial use OK
Music Flamingo Think (MF-Think) is the Chain-of-Thought version of the original Music Flamingo, a fully open, state-of-the-art Large Audio-Language Model (LALM) designed to advance music (including song) understanding in foundational audio models. MF brings together innovations in:
8.3B32K ctx Custom licence692 44Feb 2026- Same category
OmniNeural is the first fully multimodal model designed specifically for Neural Processing Units (NPUs). It natively understands text, images, and audio, and runs across PCs, mobile devices, automobile, IoT, and robotics.
4BCC BY 4.02.2K 169Aug 2025- Same category
- Commercial use OK
SenseNova-U1.5 (Preview) is a natively unified multimodal model built on NEO-unify, featuring new patch encoding and decoding layers.
17.5B256K ctx Apache 2.0159 104Jul 2026- Same category
- Commercial use OK
- [2026.04.30] Release the preview version of the 8-step inference model SenseNova-U1-8B-MoT-8step-preview. In most cases, the image generation quality of this model closely matches that of the base model (see comparison and existing issues).
17.6B256K ctx Apache 2.0163 68Jul 2026- Same category
- Commercial use OK
OmniGen2 is a powerful and efficient unified multimodal model. Unlike OmniGen v1, OmniGen2 features two distinct decoding pathways for text and image modalities, utilizing unshared parameters and a decoupled image tokenizer. OmniGen2 has competitive performance across four primary capabilities:
4BApache 2.02.3K 462Jun 2025- Same category
- Commercial use OK
Tar-7B is an open-weight omni model with 8.7B parameters from ByteDance-Seed, published on Hugging Face.
8.7B32K ctx Apache 2.01.7K 41Jul 2025- Same category
- Commercial use OK
A speech-to-speech model that reasons before it speaks. GLM-4-Voice-9B trained with reinforcement learning against a binary LLM judge on math word problems — no supervised finetuning stage, the reasoning behaviour is learned from the reward alone.
9.5B8K ctx glm-4-voice-license96 20Aug 2026- Same category