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 Audio8-TTS-Realistic-Air

120 open-weight models that do the same job as Audio8-TTS-Realistic-Air (601M TTS), 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
Edge0 logo≈1.8 GB

This release supports 23 languages, adding 12 languages compared with Preview. It uses the same Transformers inference interface as Preview. This repository includes the complete model checkpoint, its 44.1 kHz neural audio codec, tokenizer, processor, and custom Transformers code.

601MApache 2.0
25.6KOct 2026gguf
--vram
any
--gpus
--quant
  1. We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control.

    1.9BApache 2.0
    675.7KJan 2026gguf
    • Same category
    • Larger (1.9B vs 601M)
    • Commercial use OK
    vs
  2. parler-tts logo

    parler-tts-mini-v1

    parler-tts·TTS

    ≈2.5 GB

    Parler-TTS Mini v1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

    878MApache 2.0
    31.2KJun 2024gguf
    • Same category
    • Similar size (878M vs 601M)
    • Commercial use OK
    vs
  3. nineninesix logo

    kani-tts-2-en

    nineninesix·TTS

    ≈1.3 GB

    Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations

    370M125K ctx lfm1.0
    795Feb 2026
    • Same category
    • Similar size (370M vs 601M)
    vs
  4. openbmb logo

    VoxCPM2

    openbmb·TTS

    ≈5.6 GB

    VoxCPM2 is a tokenizer-free, diffusion autoregressive Text-to-Speech model — 2B parameters, 30 languages, 48kHz audio output, trained on over 2 million hours of multilingual speech data.

    2.3BApache 2.0
    973.2KApr 2026gguf
    • Same category
    • Larger (2.3B vs 601M)
    • Commercial use OK
    vs
  5. parler-tts logo≈2.6 GB

    Parler-TTS Mini Multilingual v1.1 is a multilingual extension of Parler-TTS Mini.

    938MApache 2.0
    12.2KNov 2024
    • Same category
    • Similar size (938M vs 601M)
    • Commercial use OK
    vs
  6. nari-labs logo

    Dia2-1B

    nari-labs·TTS

    ≈2.9 GB

    Dia2 is a streaming dialogue TTS model created by Nari Labs.

    1.1BApache 2.0
    2.3KNov 2025gguf
    • Same category
    • Similar size (1.1B vs 601M)
    • Commercial use OK
    vs
  7. parler-tts logo

    parler_tts_mini_v0.1

    parler-tts·TTS

    ≈1.9 GB

    Parler-TTS Mini v0.1 is a lightweight text-to-speech (TTS) model, trained on 10.5K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

    647MApache 2.0
    2KApr 2024
    • Same category
    • Similar size (647M vs 601M)
    • Commercial use OK
    vs
  8. kyutai logo

    tts-1.6b-en_fr

    kyutai·TTS

    ≈4.1 GB

    See also the pre-print research paper, the project page, the Colab example, the GitHub repository, and the repository of voices.

    1.6BCC BY 4.0
    133.4KJun 2025gguf
    • Same category
    • Larger (1.6B vs 601M)
    • Commercial use OK
    vs
  9. nineninesix logo

    kani-tts-2-pt

    nineninesix·TTS

    ≈1.3 GB

    Text-to-Speech Model with Frame-level Position Encodings, optimized for Realtime Conversations

    370M125K ctx lfm1.0
    314Feb 2026gguf
    • Same category
    • Similar size (370M vs 601M)
    vs
  10. parler-tts logo≈1.9 GB

    Parler-TTS Mini: Expresso is a fine-tuned version of Parler-TTS Mini v0.1 on the Expresso dataset. It is a lightweight text-to-speech (TTS) model that can generate high-quality, natural sounding speech.

    647MApache 2.0
    766May 2024
    • Same category
    • Similar size (647M vs 601M)
    • Commercial use OK
    vs
  11. parler-tts logo

    parler-tts-mini-v1.1

    parler-tts·TTS

    ≈2.6 GB

    Parler-TTS Mini v1.1 is a lightweight text-to-speech (TTS) model, trained on 45K hours of audio data, that can generate high-quality, natural sounding speech with features that can be controlled using a simple text prompt (e.g. gender, background noise, speaking rate, pitch and reverberation).

    938MApache 2.0
    5.7KOct 2024gguf
    • Same category
    • Similar size (938M vs 601M)
    • Commercial use OK
    vs
  12. inclusionAI logo

    Ming-omni-tts-0.5B

    inclusionAI·TTS

    ≈4.1 GB

    Ming-omni-tts is a high-performance unified audio generation model that achieves precise control over speech attributes and enables single-channel synthesis of speech, environmental sounds, and music.

    1.6BApache 2.0
    11.8KFeb 2026
    • Same category
    • Larger (1.6B vs 601M)
    • Commercial use OK
    vs
  13. nineninesix logo

    kani-tts-370m

    nineninesix·TTS

    ≈1.3 GB

    A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.

    370M125K ctx lfm1.0
    344Sept 2025gguf
    • Same category
    • Similar size (370M vs 601M)
    vs
  14. Marvis-AI logo

    marvis-tts-100m-v0.2

    Marvis-AI·TTS

    ≈1.3 GB

    Marvis is a cutting-edge conversational speech model designed to enable real-time streaming text-to-speech synthesis. Built with efficiency and accessibility in mind, Marvis addresses the growing need for high-quality, real-time voice synthesis that can run on consumer devices such as Apple…

    368MApache 2.0
    249Oct 2025
    • Same category
    • Similar size (368M vs 601M)
    • Commercial use OK
    vs
  15. OuteAI logo

    OuteTTS-0.2-500M

    OuteAI·TTS

    ≈1.6 GB

    OuteTTS-0.2-500M is our improved successor to the v0.1 release. The model maintains the same approach of using audio prompts without architectural changes to the foundation model itself.

    499M32K ctx CC BY-NC 4.0
    193Nov 2024gguf
    • Same category
    • Similar size (499M vs 601M)
    vs
  16. neuphonic logo

    neutts-2e

    neuphonic·TTS

    ≈1.0 GB

    NeuTTS-2E is a super-fast, highly realistic, on-device emotional TTS speech language model. It is an early alpha release, English-only model, supporting six emotions plus neutral (angry, disgusted, fearful, happy, sad, surprised and neutral) across four fixed speakers (emily, paul, sophie, steven).

    236MCustom licence
    1.1KJul 2026
    • Same category
    • Smaller (236M vs 601M)
    vs
  17. nari-labs logo

    Dia-1.6B-0626

    nari-labs·TTS

    ≈4.1 GB

    Dia is a 1.6B parameter text to speech model created by Nari Labs. It was pushed to the Hub using the PytorchModelHubMixin integration.

    1.6BApache 2.0
    24.9KJun 2025
    • Same category
    • Larger (1.6B vs 601M)
    • Commercial use OK
    vs
  18. Aratako logo≈2.2 GB

    This checkpoint is a minor update to Irodori-TTS-v4-Small with an improved duration predictor.

    766MMIT
    0Aug 2026gguf
    • Same category
    • Similar size (766M vs 601M)
    • Commercial use OK
    vs
  19. Aratako logo≈2.2 GB

    Irodori-TTS-v4-Small is a Japanese Text-to-Speech model based on a Rectified Flow Diffusion Transformer (RF-DiT) architecture. It combines Text (Input) + Reference Speech + Caption Text in a unified model, enabling zero-shot voice cloning, text-based voice design, and style-controlled voice cloning.

    766MMIT
    0Aug 2026
    • Same category
    • Similar size (766M vs 601M)
    • Commercial use OK
    vs
  20. sesame logo

    csm-1b

    sesame·TTS

    ≈4.0 GB

    CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.

    1.6BApache 2.0
    24.5KMar 2025gguf
    • Same category
    • Larger (1.6B vs 601M)
    • Commercial use OK
    vs
  21. nineninesix logo

    kani-tts-400m-en

    nineninesix·TTS

    ≈1.3 GB

    A high-speed, high-fidelity Text-to-Speech model optimized for real-time conversational AI applications.

    370M125K ctx lfm1.0
    64Oct 2025gguf
    • Same category
    • Similar size (370M vs 601M)
    vs
  22. freyavoice logo

    Freya-TTS

    freyavoice·TTS

    ≈0.9 GB

    FreyaTTS-small is a 183M-parameter Turkish text-to-speech model, and the open-source member of the FreyaTTS family. It is tokenizer-free at the character level (92 symbols, no phonemizer or G2P) and generates speech with a non-autoregressive conditional flow-matching DiT in the frozen AudioVAE2…

    183MApache 2.0
    4.7KJul 2026
    • Same category
    • Smaller (183M vs 601M)
    • Commercial use OK
    vs
  23. canberkkkkkk logo

    ema-lightning

    canberkkkkkk·TTS

    ? GB

    Tiny, fast and accurate Turkish text to speech. A 5.6M-parameter DiT acoustic model and a 3M-parameter vocoder: 8.6M in total, about 34 MB. Apache 2.0.

    ?BApache 2.0
    91.3KOct 2026
    • Same category
    • Commercial use OK
    vs
  24. Zyphra logo≈4.1 GB

    Zonos-v0.1 is a leading open-weight text-to-speech model trained on more than 200k hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers.

    1.6BApache 2.0
    23.1KFeb 2025gguf
    • Same category
    • Larger (1.6B vs 601M)
    • Commercial use OK
    vs