Instructions to use Mikhailo/mova-tts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Mikhailo/mova-tts with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mikhailo/mova-tts:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mikhailo/mova-tts:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Mikhailo/mova-tts:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mikhailo/mova-tts:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Mikhailo/mova-tts:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf Mikhailo/mova-tts:Q4_K_M
Use Docker
docker model run hf.co/Mikhailo/mova-tts:Q4_K_M
- Llama new
- LM Studio
- Jan
- Ollama
How to use Mikhailo/mova-tts with Ollama:
ollama run hf.co/Mikhailo/mova-tts:Q4_K_M
- Unsloth Desktop
- Pi
How to use Mikhailo/mova-tts with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mikhailo/mova-tts:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Mikhailo/mova-tts:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Mikhailo/mova-tts with Docker Model Runner:
docker model run hf.co/Mikhailo/mova-tts:Q4_K_M
- Lemonade
How to use Mikhailo/mova-tts with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mikhailo/mova-tts:Q4_K_M
Run and chat with the model
lemonade run user.mova-tts-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use Mikhailo/mova-tts with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mikhailo/mova-tts:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default Mikhailo/mova-tts:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Mikhailo/mova-tts with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Mikhailo/mova-tts:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "Mikhailo/mova-tts:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
mova-tts
Ukrainian text-to-speech with voice cloning. This model is a fine-tune of neuphonic/neutts-air on ~1780 hours of Ukrainian speech. It generates NeuCodec tokens from IPA phonemes, and it clones a voice from a 3โ12 second reference recording.
pip install mova-tts
hf auth login # NeuCodec is gated: accept the terms on neuphonic/neucodec and neucodec-onnx-decoder once
from mova_tts import MovaTTS
tts = MovaTTS() # GGUF Q8_0 from this repo; CUDA, Apple GPU or CPU
voice = tts.voice("me.wav", "ะขะพัะฝะธะน ัะตะบัั, ัะบะธะน ะทะฒััะธัั ั ะทะฐะฟะธัั.")
tts.save(tts.synthesize("ะะพะฑัะพะณะพ ะดะฝั! ะฏะบ ะฒะฐัั ัะฟัะฐะฒะธ?", voice), "out.wav")
for chunk in tts.stream("ะะตััะต ัะตัะตะฝะฝั. ะััะณะต ัะตัะตะฝะฝั.", voice):
... # float32 24 kHz chunks, the first one after 35 codes
The mova-tts package does the Ukrainian text front-end: numbers to words, stress with naholos, and IPA. It also handles streaming decoding, with left context and a crossfade.
Preset voices
mova-tts bundles four ready-made voices. They are taken from the OpenTTS datasets
(Apache-2.0), and samples are in samples/:
| preset | voice | UTMOS | WER | sample |
|---|---|---|---|---|
tetiana (default) |
female | 3.64 | 0.020 | samples/tetiana.wav |
mykyta |
male | 3.72 | 0.039 | samples/mykyta.wav |
oleksa |
male | 3.29 | 0.010 | samples/oleksa.wav |
lada |
female | 2.55 | 0.029 | samples/lada.wav |
from mova_tts import MovaTTS, preset
tts = MovaTTS()
tts.save(tts.synthesize("ะะพะฑัะพะณะพ ะดะฝั!", preset("mykyta")), "out.wav")
Files
| file | for |
|---|---|
model.safetensors, config.json, tokenizer files |
transformers (bf16, 0.7B) |
gguf/mova-tts-Q8_0.gguf (0.8 GB) |
llama.cpp, the default |
gguf/mova-tts-Q4_K_M.gguf (0.6 GB) |
llama.cpp, smaller |
The prompt format is the same as NeuTTS-Air with phoneme input:
user: Convert the text to speech:<|TEXT_PROMPT_START|>{ref IPA} {IPA}<|TEXT_PROMPT_END|>\nassistant:<|SPEECH_GENERATION_START|>{ref codes}.
The IPA must come from the mova-tts front-end (ipa-uk with stress marks). eSpeak phonemes
will not work.
Evaluation
The evaluation used 234 held-out sentences from Common Voice and audiobooks, with speakers that were never seen in training. Each speaker was cloned from a different sentence of theirs:
| WER | CER | UTMOS | speaker similarity | |
|---|---|---|---|---|
| whole utterance, Q8_0 | 0.123โ0.140 | 0.035โ0.041 | 3.45 | 0.48โ0.50 |
| streaming, Q8_0 | 0.135โ0.140 | 0.041โ0.046 | 3.37 | 0.48โ0.50 |
| streaming, Q4_K_M | 0.131โ0.135 | 0.041 | 3.33 | 0.48โ0.49 |
Each row is the range over 3 sampling seeds (2 for Q4_K_M).
WER and CER come from Whisper large-v3 transcripts. UTMOS is a predicted naturalness score from 1 to 5. Speaker similarity is the ECAPA cosine to the speaker's real recordings.
Speed (streaming, front-end included): first audio after 0.16 s on an RTX 4090 (RTF 0.14), after 1.0 s on an i9-13900KF CPU with 8 threads (RTF 0.72).
Training
- Base: neuphonic/neutts-air, a 0.7B Qwen-based speech LM (Apache-2.0). Full fine-tune in two stages: 12k steps on a 740-hour subset, then 20k steps on all the data (LR 2e-5).
- Data: ~1780 hours of Ukrainian speech: audiobooks read by professional narrators, podcasts, Common Voice, and studio voice recordings. Leading and trailing silence was trimmed, utterances with long internal pauses were dropped, and all audio was re-encoded with NeuCodec. The training data is not released.
- Text: IPA from ipa-uk. The stress labels were taken from the audio itself: the text was aligned with the Montreal Forced Aligner, and an acoustic detector marked the stress the speaker actually used. The model therefore learned real spoken stress, not dictionary stress.
Limitations
- Ukrainian only. Latin words are transliterated by the front-end.
- Each take is sampled. Sometimes a take stretches a word or pauses oddly. Generate it again with another seed.
- Cloning quality follows the reference: use a clean, single-speaker recording and its exact transcript.
Responsible use
Clone only voices you have permission to use. Audio from synthesize() carries the
imperceptible Perth watermark by default.
License
Apache-2.0, like NeuTTS-Air and NeuCodec.
- Downloads last month
- 180