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 kokoro-ru

120 open-weight models that do the same job as kokoro-ru (82M 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
zaakirio logo

kokoro-ru

zaakirio·TTS

≈0.7 GB

Russian text-to-speech at 82M parameters, running 9.8x faster than realtime on a laptop CPU with no GPU. Three fixed voices from consented studio actors.

82MOpenRAIL
72.7KJul 2026
--vram
any
--gpus
--quant
  1. 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
    1.9KNov 2026
    • Same category
    • Larger (1B vs 82M)
    • Commercial use OK
    • Newer release
    vs
  2. suno logo

    bark

    suno·TTS

    ? GB

    Bark is a transformer-based text-to-audio model created by Suno. Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. The model can also produce nonverbal communications like laughing, sighing and crying.

    ?BMIT
    12.8KApr 2023
    • Same category
    • Commercial use OK
    vs
  3. 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 82M)
    • Commercial use OK
    vs
  4. OpenMOSS-Team logo

    MOSS-TTS-Realtime

    OpenMOSS-Team·TTS

    ≈5.7 GB

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…

    2.3BApache 2.0
    11.6KFeb 2026gguf
    • Same category
    • Larger (2.3B vs 82M)
    • Commercial use OK
    vs
  5. inclusionAI logo

    Ming-3.0-audio-flash

    inclusionAI·TTS

    ≈153 GB

    Ming-3.0-audio-flash is a native audio-language model from inclusionAI. It accepts audio together with text instructions and supports speech recognition, spoken question answering, audio understanding, audio reasoning, and optional synthesized-speech responses.

    128BA6.3BMIT
    2.6KSept 2026
    • Same category
    • Larger (128B vs 82M)
    • Commercial use OK
    • Newer release
    vs
  6. OpenMOSS-Team logo

    MOSS-TTSD-v1.0

    OpenMOSS-Team·TTS

    ≈10 GB

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…

    8.4BApache 2.0
    10.7KFeb 2026
    • Same category
    • Larger (8.4B vs 82M)
    • Commercial use OK
    vs
  7. facebook logo? GB

    SeamlessM4T is a collection of models designed to provide high quality translation, allowing people from different linguistic communities to communicate effortlessly through speech and text.

    ?BCC BY-NC 4.0
    7.4KAug 2023
    • Same category
    vs
  8. IndexTeam logo

    Index-TTS

    IndexTeam·TTS

    ? GB

    IndexTTS is a GPT-style text-to-speech (TTS) model mainly based on XTTS and Tortoise. It is capable of correcting the pronunciation of Chinese characters using pinyin and controlling pauses at any position through punctuation marks.

    ?BApache 2.0
    182Mar 2025
    • Same category
    • Commercial use OK
    vs
  9. OpenMOSS-Team logo

    MOSS-VoiceGenerator

    OpenMOSS-Team·TTS

    ≈5.2 GB

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…

    2.1BApache 2.0
    7.2KFeb 2026gguf
    • Same category
    • Larger (2.1B vs 82M)
    • Commercial use OK
    vs
  10. amphion logo

    MaskGCT

    amphion·TTS

    ? GB

    You can use the following code to generate speech from text and a prompt speech.

    ?BCC BY-NC 4.0
    490Oct 2024
    • Same category
    vs
  11. ai4bharat logo

    indic-parler-tts

    ai4bharat·TTS

    ≈2.6 GB

    Indic Parler-TTS is a multilingual Indic extension of Parler-TTS Mini.

    938MApache 2.0
    183KOct 2024
    • Same category
    • Larger (938M vs 82M)
    • Commercial use OK
    vs
  12. OuteAI logo

    OuteTTS-0.1-350M

    OuteAI·TTS

    ≈1.3 GB

    OuteTTS-0.1-350M is a novel text-to-speech synthesis model that leverages pure language modeling without external adapters or complex architectures, built upon the LLaMa architecture using our Oute3-350M-DEV base model, it demonstrates that high-quality speech synthesis is achievable through a…

    362M4K ctx CC BY 4.0
    111Nov 2024
    • Same category
    • Larger (362M vs 82M)
    • Commercial use OK
    vs
  13. OpenMOSS-Team logo

    MOSS-TTS

    OpenMOSS-Team·TTS

    ≈11 GB

    MOSS‑TTS Family is an open‑source speech and sound generation model family from MOSI.AI and the OpenMOSS team. It is designed for high‑fidelity, high‑expressiveness, and complex real‑world scenarios, covering stable long‑form speech, multi‑speaker dialogue, voice/character design, environmental…

    8.5BApache 2.0
    4.9KFeb 2026
    • Same category
    • Larger (8.5B vs 82M)
    • Commercial use OK
    vs
  14. 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 82M)
    • Commercial use OK
    vs
  15. openbmb logo

    VoxCPM1.5

    openbmb·TTS

    ≈2.3 GB

    Key Improvements: - 🔊 Higher Quality: 44.1kHz sampling rate preserves more high-frequency details for better voice cloning - ⚡ More Efficient: Reduced token rate (6.25Hz) lowers computational cost while maintaining performance - 🎓 Fine-tuning Support: Train personalized voice models with SFT or…

    802MApache 2.0
    6KDec 2025gguf
    • Same category
    • Larger (802M vs 82M)
    • Commercial use OK
    vs
  16. 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 82M)
    • Commercial use OK
    vs
  17. fishaudio logo

    fish-speech-1.4

    fishaudio·TTS

    ? GB

    Fish Speech V1.4 is a leading text-to-speech (TTS) model trained on 700k hours of audio data in multiple languages.

    ?BCC BY-NC-SA 4.0
    418Sept 2024
    • Same category
    vs
  18. 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 82M)
    • Newer release
    vs
  19. Marvis-AI logo

    marvis-tts-250m-v0.1

    Marvis-AI·TTS

    ≈1.8 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…

    569MApache 2.0
    507Aug 2025
    • Same category
    • Larger (569M vs 82M)
    • Commercial use OK
    vs
  20. sbintuitions logo

    sarashina2.2-tts

    sbintuitions·TTS

    ≈2.3 GB

    Sarashina2.2-TTS is a Japanese-centric text-to-speech system built on a large language model, developed by SB Intuitions. It supports Japanese and English, delivering high pronunciation accuracy, naturalness, and stability across diverse speaking styles, with zero-shot voice generation support.

    810M8K ctx Unknown licence
    2.1KApr 2026gguf
    • Same category
    • Larger (810M vs 82M)
    vs
  21. 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 82M)
    • Commercial use OK
    vs
  22. nari-labs logo

    Dia2-2B

    nari-labs·TTS

    ≈4.8 GB

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

    1.9BApache 2.0
    6KNov 2025gguf
    • Same category
    • Larger (1.9B vs 82M)
    • Commercial use OK
    vs
  23. kyutai logo≈2.2 GB

    See also the pre-print research paper, the project page, the GitHub repository, and the evaluation pipeline.

    750MCC BY 4.0
    4.9KJul 2025
    • Same category
    • Larger (750M vs 82M)
    • Commercial use OK
    vs
  24. 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 82M)
    • Commercial use OK
    vs