selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

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.

Compare Apriel-Voice-27B-preview with the top 3
the original
ServiceNow-AI logo

Apriel-Voice-27B-preview

ServiceNow-AI·Omni

≈19 GB

An open model for speech, reasoning, and tool use from ServiceNow

27.2B256K ctx MIT
1.4KOct 2026
--vram
any
--gpus
--quant
  1. NVIDIA Nemotron 3 Nano Omni is a multimodal large language model that unifies video, audio, image, and text understanding to support enterprise-grade Q&A, summarization, transcription, and document intelligence workflows.

    33BA3B256K ctx nvidia-open-model-agreement
    96.6KApr 2026gguf
    • Same category
    • Similar size (33B vs 27.2B)
    • Commercial use OK
    vs
  2. Qwen logo≈20 GB

    Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:

    31.7BA3B64K ctx Apache 2.0
    183.7KSept 2025gguf
    • Same category
    • Similar size (31.7B vs 27.2B)
    • Commercial use OK
    vs
  3. Qwen logo≈22 GB

    Qwen3-Omni is the natively end-to-end multilingual omni-modal foundation models. It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. We introduce several architectural upgrades to improve performance and efficiency. Key features:

    35.3BA3B64K ctx Apache 2.0
    345.1KSept 2025gguf
    • Same category
    • Similar size (35.3B vs 27.2B)
    • Commercial use OK
    vs
  4. google logo

    gemma-4-12B-it

    google·Omni

    ≈11 GB

    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.

    12B256K ctx Apache 2.0
    1.6MMay 2026ollama
    • Same category
    • Smaller (12B vs 27.2B)
    • Commercial use OK
    • Widely used
    vs
  5. 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-1.1
    2.3KSept 2026gguf
    • Same category
    • Similar size (33B vs 27.2B)
    • Commercial use OK
    vs
  6. NVIDIA-NemotronLabs-AI-for-Media-Sports-Basketball is a fine-tuned multimodal large language model derived from Nemotron 3 Nano Omni.

    33B256K ctx openmdw-1.1
    961Sept 2026
    • Same category
    • Similar size (33B vs 27.2B)
    • Commercial use OK
    vs
  7. KRAFTON logo≈22 GB

    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 4.0
    1.7KJul 2026
    • Same category
    • Similar size (21.2B vs 27.2B)
    vs
  8. mistralai logo

    Voxtral-Small-24B-2507

    mistralai·Omni

    ≈16 GB

    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 2.0
    6.9KJul 2025gguf
    • Same category
    • Similar size (24.3B vs 27.2B)
    • Commercial use OK
    vs
  9. 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 2.0
    5.2KSept 2025gguf
    • Same category
    • Similar size (31.7B vs 27.2B)
    • Commercial use OK
    vs
  10. sensenova logo

    SenseNova-U1.5-8B-MoT

    sensenova·Omni

    ≈12 GB

    SenseNova-U1.5-8B-MoT is our latest native unified multimodal checkpoint for more accurate, consistent, reliable, and aesthetically compelling visual creation.

    17.5B256K ctx Apache 2.0
    3.8KAug 2026gguf
    • Same category
    • Similar size (17.5B vs 27.2B)
    • Commercial use OK
    vs
  11. nvidia logo

    NLD-Uni

    nvidia·Omni

    ≈12 GB

    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 licence
    1.2KOct 2026
    • Same category
    • Similar size (18.3B vs 27.2B)
    vs
  12. google logo

    gemma-4-E4B-it

    google·Omni

    ≈5.9 GB

    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.

    8B128K ctx Apache 2.0
    4.4MMar 2026ollama
    • Same category
    • Smaller (8B vs 27.2B)
    • Commercial use OK
    • Widely used
    vs
  13. google logo

    gemma-4-12B

    google·Omni

    ≈11 GB

    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.

    12B256K ctx Apache 2.0
    50.3KMay 2026gguf
    • Same category
    • Smaller (12B vs 27.2B)
    • Commercial use OK
    vs
  14. stepfun-ai logo

    Step-Audio-R1.1

    stepfun-ai·Omni

    ≈22 GB

    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 2.0
    673Jan 2026
    • Same category
    • Similar size (33.5B vs 27.2B)
    • Commercial use OK
    vs
  15. inclusionAI logo

    LLaDA2.0-Uni

    inclusionAI·Omni

    ≈10 GB

    LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

    16.3BA1.5B8K ctx Apache 2.0
    2.1KApr 2026
    • Same category
    • Similar size (16.3B vs 27.2B)
    • Commercial use OK
    vs
  16. BAAI logo

    Emu3.5

    BAAI·Omni

    ≈23 GB

    🔔 Latest: Emu3.5 Web & Mobile Apps and vLLM offline inference are live — see 🔥 News for details.

    34.1B32K ctx Apache 2.0
    408Oct 2025
    • Same category
    • Similar size (34.1B vs 27.2B)
    • Commercial use OK
    vs
  17. sensenova logo

    SenseNova-U1-8B-MoT

    sensenova·Omni

    ≈12 GB

    - [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 2.0
    687Apr 2026
    • Same category
    • Similar size (17.6B vs 27.2B)
    • Commercial use OK
    vs
  18. openbmb logo

    MiniCPM-o-4_5

    openbmb·Omni

    ≈7.2 GB

    A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Mulitmodal Live Streaming on Your Phone

    9.4B40K ctx Apache 2.0
    155.7KFeb 2026gguf
    • Same category
    • Smaller (9.4B vs 27.2B)
    • Commercial use OK
    vs
  19. google logo

    gemma-4-E4B

    google·Omni

    ≈5.9 GB

    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.

    8B128K ctx Apache 2.0
    452KMar 2026gguf
    • Same category
    • Smaller (8B vs 27.2B)
    • Commercial use OK
    • Widely used
    vs
  20. sensenova logo≈12 GB

    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 2.0
    161Jul 2026gguf
    • Same category
    • Similar size (17.5B vs 27.2B)
    • Commercial use OK
    vs
  21. Qwen logo

    Qwen2.5-Omni-7B

    Qwen·Omni

    ≈7.3 GB

    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.

    10.7B32K ctx Apache 2.0
    261.8KMar 2025gguf
    • Same category
    • Smaller (10.7B vs 27.2B)
    • Commercial use OK
    vs
  22. sensenova logo≈12 GB

    - [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 2.0
    162Jul 2026
    • Same category
    • Similar size (17.6B vs 27.2B)
    • Commercial use OK
    vs
  23. stepfun-ai logo

    Step-Audio-R1

    stepfun-ai·Omni

    ≈22 GB

    Step-Audio-R1 is the first audio language model to successfully unlock Chain-of-Thought (CoT) reasoning. It decisively solves the "inverted scaling" problem that plagues existing models, where performance degrades with longer reasoning.

    33.5BApache 2.0
    119Nov 2025
    • Same category
    • Similar size (33.5B vs 27.2B)
    • Commercial use OK
    vs
  24. tencent logo

    WeVisCut

    tencent·Omni

    ≈7.1 GB

    WeVisCut is a 9B tool-using agent that turns knowledge articles or narration scripts into multi-minute edited videos. At each step, it reads the current editing state and selects one of 12 tools for planning, narration, asset retrieval, composition, inspection, or repair.

    9.4B256K ctx Custom licence
    16.6KSept 2026gguf
    • Same category
    • Smaller (9.4B vs 27.2B)
    vs