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.

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
1.5KOct 2026
--vram
any
--gpus
--quant
  1. OpenMOSS-Team logo

    MOSS-Audio-4B-Thinking

    OpenMOSS-Team·Omni

    ≈4.7 GB

    MOSS-Audio is an open-source audio understanding model from MOSI.AI, the OpenMOSS team, and Shanghai Innovation Institute.

    5.2B40K ctx Apache 2.0
    657Apr 2026
    • Same category
    • Smaller (5.2B vs 27.2B)
    • Commercial use OK
    vs
  2. IDEA-Research logo

    Rex-Omni

    IDEA-Research·Omni

    ≈3.2 GB

    This model is Rex-Omni, a 3B-parameter Multimodal Large Language Model (MLLM) presented in the paper "Detect Anything via Next Point Prediction". It is compatible with the Hugging Face transformers library and is licensed under the IDEA License 1.0.

    4.1B125K ctx Custom licence
    14.7KOct 2025
    • Same category
    • Smaller (4.1B vs 27.2B)
    vs
  3. LiquidAI logo

    LFM3-Omni-2B

    LiquidAI·Omni

    ≈2.2 GB

    LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.

    2.2B125K ctx lfm1.0
    27.3KOct 2026ollama
    • Same category
    • Smaller (2.2B vs 27.2B)
    • Newer release
    vs
  4. FreedomIntelligence logo

    Janus-4o-7B

    FreedomIntelligence·Omni

    ≈5.9 GB

    Janus-4o is a multimodal large language model (MLLM) capable of both text-to-image and text-and-image-to-image generation. It is fine-tuned from Janus-Pro-7B using the ShareGPT-4o-Image dataset to align Janus-Pro with GPT-4o image generation capabilities.

    7.4B16K ctx MIT
    123Jun 2025
    • Same category
    • Smaller (7.4B vs 27.2B)
    • Commercial use OK
    vs
  5. BAAI logo

    Emu3-Stage1

    BAAI·Omni

    ≈6.2 GB

    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 2.0
    199Oct 2024
    • Same category
    • Smaller (8.5B vs 27.2B)
    • Commercial use OK
    vs
  6. sarvamai logo

    shuka-1

    sarvamai·Omni

    ≈6.7 GB

    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 License
    233Aug 2024
    • Same category
    • Smaller (8.7B vs 27.2B)
    vs
  7. google logo≈1.0 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.

    423M256K ctx Apache 2.0
    36.8KMay 2026gguf
    • Same category
    • Smaller (423M vs 27.2B)
    • Commercial use OK
    vs
  8. LiquidAI logo

    LFM3-Audio-2B

    LiquidAI·Omni

    ≈2.2 GB

    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.

    2B125K ctx lfm1.0
    17.5KSept 2026ollama
    • Same category
    • Smaller (2B vs 27.2B)
    vs
  9. Qwen logo

    Qwen-Audio

    Qwen·Omni

    ≈6.5 GB

    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 licence
    1.6KNov 2023
    • Same category
    • Smaller (8.4B vs 27.2B)
    vs
  10. google logo≈0.6 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.

    78M128K ctx Apache 2.0
    33.3KApr 2026gguf
    • Same category
    • Smaller (78M vs 27.2B)
    • Commercial use OK
    vs
  11. nvidia logo

    audio-flamingo-3

    nvidia·Omni

    ? GB

    Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio-Language Models

    ?BCustom licence
    715Jul 2025
    • Same category
    vs
  12. LiquidAI logo

    d1-omni-600M

    LiquidAI·Omni

    ≈1.1 GB

    d1-omni-600M is a 600M parameter decision model built on LFM2.5-Encoder-350M. You give it a state (text or JSON, with images or a voice clip) and a set of named questions.

    587M125K ctx lfm1.0
    8.4KOct 2026gguf
    • Same category
    • Smaller (587M vs 27.2B)
    vs
  13. google logo≈0.6 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.

    79M128K ctx Apache 2.0
    24.3KApr 2026gguf
    • Same category
    • Smaller (79M vs 27.2B)
    • Commercial use OK
    vs
  14. LiquidAI logo

    d1-Omni-2B

    LiquidAI·Omni

    ≈2.2 GB

    d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.

    2.2B125K ctx lfm1.0
    6.5KOct 2026ollama
    • Same category
    • Smaller (2.2B vs 27.2B)
    • Newer release
    vs
  15. google logo

    gemma-3n-E2B

    google·Omni

    ≈4.2 GB

    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 Use
    614Jun 2025gguf
    • Same category
    • Smaller (5.4B vs 27.2B)
    vs
  16. FlashLabs logo

    Chroma-4B

    FlashLabs·Omni

    ≈4.9 GB

    FlashLabs Chroma 1.0: A Real-Time End-to-End Spoken Dialogue Model with Personalized Voice Cloning

    5.9BApache 2.0
    46Nov 2025
    • Same category
    • Smaller (5.9B vs 27.2B)
    • Commercial use OK
    vs
  17. microsoft logo

    OmniParser

    microsoft·Omni

    ? GB

    OmniParser is a general screen parsing tool, which interprets/converts UI screenshot to structured format, to improve existing LLM based UI agent.

    ?BMIT
    1.6KOct 2024
    • Same category
    • Commercial use OK
    vs
  18. NexaAI logo

    OmniNeural-4B

    NexaAI·Omni

    ≈3.6 GB

    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 4.0
    2.2KAug 2025
    • Same category
    • Smaller (4B vs 27.2B)
    • Commercial use OK
    vs
  19. We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.

    8B128K ctx Apache 2.0
    51Sept 2024gguf
    • Same category
    • Smaller (8B vs 27.2B)
    • Commercial use OK
    vs
  20. OmniGen2 logo

    OmniGen2

    OmniGen2·Omni

    ≈3.6 GB

    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 2.0
    2.3KJun 2025gguf
    • Same category
    • Smaller (4B vs 27.2B)
    • Commercial use OK
    vs
  21. stepfun-ai logo

    Step-Audio-Chat

    stepfun-ai·Omni

    ≈112 GB

    This repository contains the Multimodal Large Language Model (LLM) component of Step-Audio. It is a 130 billion parameter multimodal LLM that is responsible for understanding and generating human speech.

    132B32K ctx Apache 2.0
    267Feb 2025
    • Same category
    • Larger (132B vs 27.2B)
    • Commercial use OK
    vs
  22. adventists-ai logo

    Sophon-Realtime-v1

    adventists-ai·Omni

    ? GB

    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 2.0
    0Nov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  23. inclusionAI logo

    Duo-1.0-distill

    inclusionAI·Omni

    ? GB

    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-license
    0Nov 2026
    • Same category
    • Newer release
    vs
  24. gpt-omni logo

    mini-omni2

    gpt-omni·Omni

    ? GB

    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.

    ?BMIT
    136Oct 2024gguf
    • Same category
    • Commercial use OK
    vs