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 ZONOS3-Mini-hf

120 open-weight models that do the same job as ZONOS3-Mini-hf (1B 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
Zyphra logo

ZONOS3-Mini-hf

Zyphra·TTS

≈2.8 GB

ZONOS3-Mini is Zyphra's compact text-to-speech model supporting 43 languages, with about 100 million active parameters per token (800 million total in the backbone).

1BApache 2.0
1.3KNov 2026
--vram
any
--gpus
--quant
  1. 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 1B)
    • Commercial use OK
    vs
  2. 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 1B)
    • Commercial use OK
    vs
  3. ai4bharat logo

    IndicF5

    ai4bharat·TTS

    ≈1.3 GB

    We release IndicF5, a near-human polyglot Text-to-Speech (TTS) model trained on 1417 hours of high-quality speech from Rasa, IndicTTS, LIMMITS, and IndicVoices-R.

    351MMIT
    40.4KMar 2025
    • Same category
    • Smaller (351M vs 1B)
    • Commercial use OK
    vs
  4. 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
    1.9KApr 2024
    • Same category
    • Similar size (647M vs 1B)
    • Commercial use OK
    vs
  5. maya-research logo

    maya1

    maya-research·TTS

    ≈4.4 GB

    Maya-1 is an open-weight text-to-speech model from Maya Research that combines natural-language voice descriptions with inline expressive controls. It generates speech as discrete audio tokens, which are decoded into a 24 kHz waveform.

    3.3B128K ctx Apache 2.0
    8.3KOct 2025gguf
    • Same category
    • Larger (3.3B vs 1B)
    • Commercial use OK
    vs
  6. rumik-ai logo

    rumik-oss-1

    rumik-ai·TTS

    ≈4.5 GB

    rumik-oss 1 is a 3b multilingual text-to-speech model from rumik ai, trained on fewer than 70,000 hours of speech while performing competitively with existing TTS models. it combines code-switched synthesis, description-conditioned delivery, and inline vocalization control, with 24 khz audio output.

    3.4B8K ctx CC BY-NC 4.0
    900Sept 2026
    • Same category
    • Larger (3.4B vs 1B)
    vs
  7. mispeech logo

    midashenglm-gen

    mispeech·TTS

    ≈7.0 GB

    MiDashengLM-Gen is an end-to-end framework that uses a pre-trained Large Language Model and audio tokenizer as the backbone, combined with per-token conditional flow matching for autoregressive, variable-length mixed-audio scene generation.

    2.9BApache 2.0
    240Aug 2026
    • Same category
    • Larger (2.9B vs 1B)
    • Commercial use OK
    vs
  8. fishaudio logo

    s2-pro

    fishaudio·TTS

    ≈5.9 GB

    Fish Audio S2 Pro is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture.

    4.6Bfish-audio-research-license
    43KMar 2026gguf
    • Same category
    • Larger (4.6B vs 1B)
    vs
  9. 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
    789May 2024
    • Same category
    • Similar size (647M vs 1B)
    • Commercial use OK
    vs
  10. Supertone logo

    supertonic-3

    Supertone·TTS

    ? GB

    Supertonic is a lightweight text-to-speech system for local inference. It runs with ONNX Runtime entirely on your device, with no cloud call required for synthesis.

    ?BOpenRAIL
    84.4KMay 2026gguf
    • Same category
    vs
  11. OpenMOSS-Team logo

    MOSS-TTSD-v0.5

    OpenMOSS-Team·TTS

    ≈5.1 GB

    MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English. It can transform dialogue scripts between two speakers into natural, expressive conversational speech.

    2B32K ctx Apache 2.0
    175Jul 2025gguf
    • Same category
    • Similar size (2B vs 1B)
    • Commercial use OK
    vs
  12. 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
    786Feb 2026
    • Same category
    • Smaller (370M vs 1B)
    vs
  13. IndexTeam logo

    IndexTTS-2.5

    IndexTeam·TTS

    ? GB

    IndexTTS-2.5 is a zero-shot text-to-speech model that clones a voice from a single reference audio clip. It supports Chinese, English, Japanese, Spanish and Arabic, with cross-lingual voice transfer and emotion control disentangled from timbre.

    ?Bbilibili-model-license
    31.5KAug 2026gguf
    • Same category
    vs
  14. parler-tts logo

    parler-tts-large-v1

    parler-tts·TTS

    ≈5.7 GB

    Parler-TTS Large v1 is a 2.2B-parameters 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).

    2.3BApache 2.0
    4.6KAug 2024gguf
    • Same category
    • Larger (2.3B vs 1B)
    • Commercial use OK
    vs
  15. canopylabs logo

    orpheus-3b-0.1-ft

    canopylabs·TTS

    ≈5.0 GB

    03/18/2025 – We are releasing our 3B Orpheus TTS model with additional finetunes. Code is available on GitHub: CanopyAI/Orpheus-TTS

    3.8B128K ctx Apache 2.0
    49KMar 2025gguf
    • Same category
    • Larger (3.8B vs 1B)
    • Commercial use OK
    vs
  16. 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
    306Feb 2026gguf
    • Same category
    • Smaller (370M vs 1B)
    vs
  17. google logo? GB

    Magenta RealTime 2 is offered under a combination of licenses: the codebase is licensed under Apache 2.0, and the model weights under Creative Commons Attribution 4.0 International. In addition, we specify the following usage terms:

    ?BCC BY 4.0
    18.4KMay 2026gguf
    • Same category
    • Commercial use OK
    vs
  18. zeroweight-ai logo

    ZeroTTS

    zeroweight-ai·TTS

    ? GB

    The most accurate open Vietnamese TTS we know of — 4× fewer word errors than the next best model, and it runs faster than real time on a laptop CPU.

    ?BMIT
    7.8KAug 2026
    • Same category
    • Commercial use OK
    vs
  19. OpenMOSS-Team logo

    MOSS-TTSD-v0

    OpenMOSS-Team·TTS

    ≈5.1 GB

    MOSS-TTSD (text to spoken dialogue) is an open-source bilingual spoken dialogue synthesis model that supports both Chinese and English. It can transform dialogue scripts between two speakers into natural, expressive conversational speech.

    2BApache 2.0
    41Jun 2025
    • Same category
    • Similar size (2B vs 1B)
    • Commercial use OK
    vs
  20. 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
    311Sept 2025gguf
    • Same category
    • Smaller (370M vs 1B)
    vs
  21. 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
    • Smaller (368M vs 1B)
    • Commercial use OK
    vs
  22. mistralai logo

    Voxtral-4B-TTS-2603

    mistralai·TTS

    ≈5.3 GB

    Voxtral TTS is a frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents. The model is released with BF16 weights and a set of reference voices.

    4BCC BY-NC 4.0
    2.7KNov 2025gguf
    • Same category
    • Larger (4B vs 1B)
    vs
  23. TeraSpace logo

    TeraTTSv2

    TeraSpace·TTS

    ? GB

    If TeraTTSv2 is useful to you, consider supporting its development. Thank you for your support!

    ?Bterattsv2-openrail-m-commercial-attribution
    3.9KAug 2026
    • Same category
    vs
  24. 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
    154Nov 2024gguf
    • Same category
    • Smaller (499M vs 1B)
    vs