Instructions to use moiralabs/GenosTTSAir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moiralabs/GenosTTSAir with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="moiralabs/GenosTTSAir")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("moiralabs/GenosTTSAir") model = AutoModelForCausalLM.from_pretrained("moiralabs/GenosTTSAir", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)
GenosTTSAir (male voice)
Male-voice Greek fine-tune of NeuTTS-Air for the MoiraAI voice stack: a single-voice speech language model that turns text into NeuCodec audio tokens in Genos's voice. It is fine-tuned to produce this one specific voice — not to clone arbitrary voices.
Built off the open NeuTTS LM + codec design — small on-device backbone, 50 Hz single-codebook neural codec, GGUF-friendly for phones and laptops.
Samples
Reference transcript (samples/greek.txt): "Ο βροντόσαυρος έψαχνε τροφή στην αυλή."
| clip | audio |
|---|---|
| Reference voice | |
| Generated example |
Model details
- Voice: male, single voice — Genos. Fine-tuned to speak as Genos; always generate with a reference clip of Genos's voice.
- Backbone: Qwen2-family causal LM (0.5B scale; NeuTTS-Air builds on Qwen2.5-0.5B) — 24 layers, hidden size 896, 14 attention heads / 2 KV heads, bfloat16.
- Vocabulary: 217,652 tokens — Qwen2 BPE plus added audio tokens
(
added_tokens.json). - Codec: neuphonic/neucodec (50 Hz, single codebook) — this repo holds the LM half only.
- Input: phonemised text (handled automatically by the
neuttspackage viaespeak-ng). - Operating window: 2048 tokens ≈ ~30 s of audio including the voice prompt (config allows up to 32768 positions).
- Training: fine-tuned for 1 epoch (15,188 steps) — loss curve in
trainer_state.json. - Sampling defaults: temperature 0.7, top-k 20, top-p 0.8,
repetition penalty 1.1 (
generation_config.json). - Base project: neuphonic/neutts (NeuTTS-Air is Apache 2.0).
Usage
Requires espeak-ng on your system
(install guide).
This is a public repo — no login needed. Note: the neuphonic/neucodec
codec repo is auto-gated, so accept access once while logged in; the
backbone itself needs nothing.
pip install neutts soundfile
from neutts import NeuTTS
import soundfile as sf
tts = NeuTTS(
backbone_repo="moiralabs/GenosTTSAir",
backbone_device="cpu",
codec_repo="neuphonic/neucodec",
codec_device="cpu",
language="el", # required: non-Neuphonic backbones raise without it
)
input_text = "Γεια σου! Χαίρομαι που σε γνωρίζω."
ref_text = open("samples/greek.txt").read().strip() # transcript of Genos's ref clip
ref_codes = tts.encode_reference("samples/greek.wav") # short clip of Genos's voice
wav = tts.infer(input_text, ref_codes, ref_text)
sf.write("out.wav", wav, 24000)
For on-device/quantised inference, convert the backbone to GGUF and
pass the .gguf repo as backbone_repo with llama-cpp-python
installed (pip install "neutts[llama]") — same pattern as the
upstream neutts-air-q4-gguf /
neutts-air-q8-gguf releases.
Other inference paths (see examples/ in
neuphonic/neutts):
- Pre-encoded references:
encode_reference()can be run once and the codes saved withtorch.save(ref_codes, "ref.pt")to skip re-encoding on every run. - ONNX decoder: pass
codec_repo="neuphonic/neucodec-onnx-decoder"(needsonnxruntimeand a pre-encoded.ptreference) for lower-latency decoding without the codec encoder. - Streaming:
tts.infer_stream(...)yields audio chunks as they generate, but only works with GGUF backbones (needspyaudio).
Notes
CPU-only machines: plain
pip install neuttspulls CUDA torch plus gigabytes of NVIDIA deps. Skip them by installing the CPU builds first (keep their versions matched to each other):pip install torch torchaudio torchvision --index-url https://download.pytorch.org/whl/cputorchaovstorchtune: currenttorchaoremovedNF4Tensor, whichtorchtune0.6.1 still imports (No module named 'torchao.dtypes.nf4tensor'). Until upstream agrees, stub it — those names only serve quantization helpers inference never calls:# torchao/dtypes/nf4tensor.py class NF4Tensor: pass def linear_nf4(*a, **k): raise RuntimeError("nf4 shim") def to_nf4(*a, **k): raise RuntimeError("nf4 shim") def implements(*a, **k): return lambda f: f
Files
model.safetensors— backbone weights (Git LFS)config.json,generation_config.json— model and sampling configvocab.json,merges.txt,added_tokens.json— tokenizertrainer_state.json,training_args.bin— training provenancechat_template.jinja— Qwen chat template (kept from the base model)samples/greek.wav,samples/greek.txt— Genos reference clip + transcriptsamples/greek_output.wav— example output in Genos's voice
Limitations
- Tuned for short Greek utterances.
- Research-grade voice: expect artifacts on long or out-of-domain text.
- Audio generated through the NeuTTS pipeline carries a watermark.
Disclaimer
Genos and Moira are fictional AI personas created for the MoiraAI project's own products. Do not use these models to impersonate any real individual or to create misleading recordings, robocalls, scams, or disinformation. You are responsible for complying with all applicable laws on synthetic media and voice rights. We do not condone any misuse of these models.
Acknowledgments
Special thanks to Neuphonic — pioneers of the open text-to-speech space — for releasing NeuTTS and NeuCodec as open source. This model would not exist without their work.
- Downloads last month
- 20