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. owensong logo

    Inflect-Mini-v3

    owensong·TTS

    ? GB

    A complete voice. A smaller footprint. Six English voices. Local generation. More ways to make speech your own.

    ?BApache 2.0
    965Nov 2026
    • Same category
    • Commercial use OK
    • Newer release
    vs
  2. tencent logo

    AuK

    tencent·TTS

    ? GB

    AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…

    ?BMIT
    1.3KAug 2026gguf
    • Same category
    • Commercial use OK
    vs
  3. IndexTeam logo

    IndexTTS-2

    IndexTeam·TTS

    ? GB

    IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech

    ?BUnknown licence
    25.9KJun 2025
    • Same category
    vs
  4. OpenMOSS-Team logo≈5.9 GB

    MOSS-TTS-Local-Transformer-v1.5 is continued from MOSS-TTS-Local-Transformer-v1.0. It preserves the main 1.0 capabilities, including zero-shot voice cloning, long-form speech generation, token-level duration control, Pinyin/IPA pronunciation control, multilingual synthesis, and code-switching.

    4.6BApache 2.0
    70.8KJun 2026gguf
    • Same category
    • Larger (4.6B vs 601M)
    • Commercial use OK
    vs
  5. bosonai logo

    higgs-tts-3-4b

    bosonai·TTS

    ≈6.0 GB

    Higgs TTS 3 is built for voice chat: it speaks, not just reads. It turns model responses into expressive conversational speech across 100+ languages, with zero-shot voice cloning and inline control over emotion, style, prosody, pauses, and sound effects.

    4.7Bboson-higgs-tts-3-research-and-non-commercial-license
    84.3KJun 2026
    • Same category
    • Larger (4.7B vs 601M)
    vs
  6. tencent logo

    AuK-Flash

    tencent·TTS

    ? GB

    AuK is a 1.5B foundation model for speech generation and editing. Trained on millions of hours of diverse audio data, AuK supports zero-shot and instruction-based TTS, content and acoustic editing, paralinguistic editing, speech enhancement, and source separation through a unified natural-language…

    ?BMIT
    648Aug 2026
    • Same category
    • Commercial use OK
    vs
  7. KittenML logo

    kitten-tts-2-mini

    KittenML·TTS

    ≈0.7 GB

    82M parameters, 16 languages, 118 voices, 24 kHz. ONNX with int8 weights (82.7 MB; runs on CPU, no PyTorch needed), and the float32 PyTorch weights.

    82MApache 2.0
    8.4KNov 2026
    • Same category
    • Smaller (82M vs 601M)
    • Commercial use OK
    • Newer release
    vs
  8. SWivid logo

    E2-TTS

    SWivid·TTS

    ? GB

    E2-TTS is an open-weight tts model from SWivid, published on Hugging Face.

    ?BCC BY-NC 4.0
    75.4KOct 2024
    • Same category
    vs
  9. Oomni logo

    mithi-v1-flash

    Oomni·TTS

    ≈0.7 GB

    A small text-to-speech model for 11 Indian languages, with two voices: Satvik (male) and Charvi (female).

    99MApache 2.0
    1.5KNov 2026
    • Same category
    • Smaller (99M vs 601M)
    • Commercial use OK
    • Newer release
    vs
  10. 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
    271Aug 2026
    • Same category
    • Larger (2.9B vs 601M)
    • Commercial use OK
    vs
  11. 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
    7.9KOct 2025gguf
    • Same category
    • Larger (3.3B vs 601M)
    • Commercial use OK
    vs
  12. 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
    869Sept 2026
    • Same category
    • Larger (3.4B vs 601M)
    vs
  13. 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 601M)
    vs
  14. 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
    208Jul 2025gguf
    • Same category
    • Larger (2B vs 601M)
    • Commercial use OK
    vs
  15. Zyphra logo

    ZONOS2

    Zyphra·TTS

    ? GB

    ZONOS2 is our latest text-to-speech model trained on more than 6 million hours of varied multilingual speech, delivering expressiveness and quality on par with—or even surpassing—top TTS providers at low latency with MoE. ZONOS2 excels at high-fidelity and naturalistic voice cloning.

    ?BApache 2.0
    516Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  16. microsoft logo

    speecht5_tts

    microsoft·TTS

    ? GB

    This model was introduced in SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing by Junyi Ao, Rui Wang, Long Zhou, Chengyi Wang, Shuo Ren, Yu Wu, Shujie Liu, Tom Ko, Qing Li, Yu Zhang, Zhihua Wei, Yao Qian, Jinyu Li, Furu Wei.

    ?BMIT
    410KFeb 2023gguf
    • Same category
    • Commercial use OK
    vs
  17. owensong logo

    Inflect-Micro-v2

    owensong·TTS

    ? GB

    New: public adaptation toolkit Prepare data, audit train/validation splits, adapt a fixed voice or language, resume training, evaluate checkpoints, and export PyTorch or ONNX packages with the Inflect adaptation toolkit.

    ?BApache 2.0
    332Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  18. 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
    4.8KAug 2024gguf
    • Same category
    • Larger (2.3B vs 601M)
    • Commercial use OK
    vs
  19. ResembleAI logo

    Dramabox

    ResembleAI·TTS

    ? GB

    Built on LTX-2 by Lightricks. Dramabox is Resemble AI's expressive TTS, trained on top of the LTX-2.3 audio branch under the LTX-2 Community License. Huge thanks to the Lightricks team for open-sourcing the base.

    ?Bltx-2-community
    466Apr 2026
    • Same category
    vs
  20. myshell-ai logo

    MeloTTS-English

    myshell-ai·TTS

    ? GB

    MeloTTS is a high-quality multi-lingual text-to-speech library by MIT and MyShell.ai. Supported languages include:

    ?BMIT
    139.5KFeb 2024
    • Same category
    • Commercial use OK
    vs
  21. owensong logo

    Inflect-Nano-v2

    owensong·TTS

    ? GB

    New: public adaptation toolkit Prepare data, audit train/validation splits, adapt a fixed voice or language, resume training, evaluate checkpoints, and export PyTorch or ONNX packages with the Inflect adaptation toolkit.

    ?BApache 2.0
    211Jun 2026gguf
    • Same category
    • Commercial use OK
    vs
  22. 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
    48.6KMar 2025gguf
    • Same category
    • Larger (3.8B vs 601M)
    • Commercial use OK
    vs
  23. fishaudio logo

    drama-3

    fishaudio·TTS

    ≈43 GB

    Fish Audio Drama 3 is Fish Audio's new-generation text-to-speech model, built for multi-character scenes and long-form content. It supports multi-speaker generation, voice cloning and natural-language control.

    35.9BA4.7Bfish-audio-research-license
    44.4KOct 2026gguf
    • Same category
    • Larger (35.9B vs 601M)
    vs
  24. zai-org logo

    GLM-TTS

    zai-org·TTS

    ? GB

    GLM-TTS is a high-quality text-to-speech (TTS) synthesis system based on large language models, supporting zero-shot voice cloning and streaming inference. The system adopts a two-stage architecture combining an LLM for speech token generation and a Flow Matching model for waveform synthesis.

    ?BMIT
    714Dec 2025
    • Same category
    • Commercial use OK
    vs