An open model for speech, reasoning, and tool use from ServiceNow
Alternatives to Apriel-Voice-27B-preview
114 open-weight models that do the same job as Apriel-Voice-27B-preview (27.2B 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.
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 Use7.8K 943Jun 2025- Same category
- Smaller (7.8B vs 27.2B)
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
- Smaller (8.3B vs 27.2B)
- 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 licence723 44Feb 2026- Same category
- Smaller (8.3B vs 27.2B)
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
- Smaller (8.7B vs 27.2B)
- Commercial use OK
Qwen2.5-Omni is an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses in a streaming manner.
5.5B32K ctx Qwen Research License99K 381Apr 2025- Same category
- Smaller (5.5B vs 27.2B)
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 4.0646 117Jun 2026- Same category
- Smaller (7B vs 27.2B)
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 27.2B)
- Commercial use OK
Both directories contain model weights and custom Hugging Face Transformers code. The asynchronous Realtime-Venus-Harness and its external tool integrations live in the GitHub repository.
?BApache 2.02.4K 140Sept 2026- Same category
- Commercial use OK
Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Given a single input — a document page, a natural image, a chart / flowchart, a geometry figure, an audio clip or an audio-visual video — it produces one structured JSON envelope that covers both perception (layout elements, text…
5.3B1M ctx youtu-parsing2.4K 132Oct 2026- Same category
- Smaller (5.3B vs 27.2B)
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 MIT17.5K 3.7KJan 2025- Same category
- Smaller (7B vs 27.2B)
- Commercial use OK
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.
8B8K ctx MIT847 173Sept 2025- Same category
- Smaller (8B vs 27.2B)
- Commercial use OK
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions.
8B8K ctx MIT673 61Sept 2025- Same category
- Smaller (8B vs 27.2B)
- 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.
5.4B32K ctx Gemma Terms of Use25.9K 336Jun 2025- Same category
- Smaller (5.4B vs 27.2B)
Qwen2-Audio is the new series of Qwen large audio-language models. Qwen2-Audio is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. We introduce two distinct audio interaction modes:
8.4BApache 2.06.7K 185Jul 2024- Same category
- Smaller (8.4B vs 27.2B)
- 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 2.0308 54Jul 2026- Same category
- Smaller (6.2B vs 27.2B)
- 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 Use737 154Jun 2025- Same category
- Smaller (7.8B vs 27.2B)
MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.
5.2B40K ctx Apache 2.02.3K 91Apr 2026- Same category
- Smaller (5.2B vs 27.2B)
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
420M256K ctx Apache 2.0328.5K 205Apr 2026- Same category
- Smaller (420M vs 27.2B)
- Commercial use OK
SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
5.1B128K ctx MIT1.1K 18May 2026- Same category
- Smaller (5.1B vs 27.2B)
- Commercial use OK
Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
470M256K ctx Apache 2.0175.9K 347Apr 2026- Same category
- Smaller (470M vs 27.2B)
- 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.
8.5B9K ctx Apache 2.0755 229Sept 2024- Same category
- Smaller (8.5B vs 27.2B)
- 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 2.0875 134Jan 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
OmniLMM-12B is the most capable version of OmniLMM currently. The model is built based on EVA02-5B and Zephyr-7B-β, connected with a perceiver resampler layer, and trained on multimodal data in a curriculum fashion. The model has three notable features:
12B32K ctx Unknown licence172 74Jan 2024- Same category
- Smaller (12B vs 27.2B)