LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.
Alternatives to LFM3-Audio-2B
114 open-weight models that do the same job as LFM3-Audio-2B (2B omni), 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.
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
16.3BA1.5B8K ctx Apache 2.02.2K 252Apr 2026- Same category
- Larger (16.3B vs 2B)
- 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 2.09.1K 1.2KMay 2025- Same category
- Larger (14.7B vs 2B)
- Commercial use OK
OmniParser is a general screen parsing tool, which interprets/converts UI screenshot to structured format, to improve existing LLM based UI agent.
?BMIT1.6K 1.7KOct 2024- Same category
- Commercial use OK
NLD-Uni is a unified multimodal model for image understanding and image generation. It combines a diffusion language model with specialized visual components and a mixture-of-transformers design.
18.3B128K ctx Unknown licence1.3K 12Oct 2026- Same category
- Larger (18.3B vs 2B)
- Newer release
NVIDIA-NemotronLabs-AI-for-Media-Sports-Tennis is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni. It was further trained on an in-house NVIDIA tennis dataset of manually labeled point-level video clips to specialize in tennis match understanding.
33B256K ctx openmdw-1.12.4K 28Sept 2026- Same category
- Larger (33B vs 2B)
- Commercial use OK
We introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction ! By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences.
8.5B5K ctx Apache 2.0199 30Oct 2024- Same category
- Larger (8.5B vs 2B)
- Commercial use OK
Qwen-Audio (Qwen Large Audio Language Model) is the multimodal version of the large model series, Qwen (abbr. Tongyi Qianwen), proposed by Alibaba Cloud. Qwen-Audio accepts diverse audio (human speech, natural sound, music and song) and text as inputs, outputs text.
8.4B2K ctx Unknown licence1.6K 169Nov 2023- Same category
- Larger (8.4B vs 2B)
An open model for speech, reasoning, and tool use from ServiceNow
27.2B256K ctx MIT1.5K 97Oct 2026- Same category
- Larger (27.2B vs 2B)
- Commercial use OK
- Newer release
NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni.
33B256K ctx openmdw-1.11.2K 9Sept 2026- Same category
- Larger (33B vs 2B)
- Commercial use OK
- Newer release
Shuka v1 is a language model which natively understands audio in Indic languages. It is an encoder-decoder model built by combining two models: - Our state-of-the-art, in-house, audio encoder: Saaras v1 - Meta’s Llama3-8B-Instruct as the decoder
8.7BLlama 3 Community License238 99Aug 2024- Same category
- Larger (8.7B vs 2B)
A.X K2 Raon-Speech is a bilingual English/Korean speech language model with approximately 21.2B total parameters and 3.5B active parameters.
21.2BA3B128K ctx CC BY-NC 4.01.4K 114Jul 2026- Same category
- Larger (21.2B vs 2B)
- [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 2.0706 295Apr 2026- Same category
- Larger (17.6B vs 2B)
- Commercial use OK
We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.
8B128K ctx Apache 2.046 35Sept 2024- Same category
- Larger (8B vs 2B)
- Commercial use OK
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
?BApache 2.00 255Nov 2026- Same category
- Commercial use OK
- Newer release
Duo is a full-duplex multimodal world model for real-time audio-visual interaction. This repository contains the four-step distilled Realization weights for Duo 1.0.
?Bminimax-h3-community-license0 11Nov 2026- Same category
- Newer release
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 2.0166 104Jul 2026- Same category
- Larger (17.5B vs 2B)
- Commercial use OK
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.
24.3B128K ctx Apache 2.07.5K 557Jul 2025- Same category
- Larger (24.3B vs 2B)
- Commercial use OK
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 2.04.4K 264Sept 2025- Same category
- Larger (31.7B vs 2B)
- Commercial use OK
Mini-Omni2 is an omni-interactive model. It can understand image, audio and text inputs and has end-to-end voice conversations with users. Featuring real-time voice output, omni-capable multimodal understanding and flexible interaction ability with interruption mechanism while speaking.
?BMIT137 292Oct 2024- 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 2.0162 68Jul 2026- Same category
- Larger (17.6B vs 2B)
- 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
- Larger (104B vs 2B)
- 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 MIT766 223Mar 2026- Same category
- Larger (74.3B vs 2B)
- 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 2.0948 193Jan 2026- Same category
- Larger (33.5B vs 2B)
- Commercial use OK
If you find TeleStyleV2 useful for your research and applications, please cite using this BibTeX:
?BApache 2.00 40Jun 2026- Same category
- Commercial use OK