Downloads · 30 days
8
4% of all-time downloads
raditotev/bg-tts-v5-mlx
bg-tts-v5-mlx is a text-to-speech model from raditotev. Use it when you need text read aloud. It is set up for mlx. The card lists the license as mit.
Native MLX port of beleata74/bg-tts-v5 for Apple Silicon (M1/M2/M3/M4).
Downloads · 30 days
8
4% of all-time downloads
All-time downloads
202
Public
Parameters
251M
1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors1 GB · 100%
From the Hugging Face model README
Native MLX port of beleata74/bg-tts-v5 for Apple Silicon (M1/M2/M3/M4).
No CUDA, no NeMo, no PyTorch required. Runs fully on Apple Silicon via MLX.
pip install mlx soundfile numpy
pip install "nanocodec-mlx @ git+https://github.com/nineninesix-ai/nanocodec-mlx.git"
from tts_mlx.inference import synthesize
synthesize(
checkpoint=".", # path to this repo
text="Здравейте, аз съм българска система за синтез на реч.",
output="output.wav",
speaker_id=0, # 0 = AI voice, 1 = audiobook narrator
temperature=0.25,
top_k=50,
top_p=0.8,
)
| Speaker | Description | Best text length |
|---|---|---|
| 0 | AI-generated, clear & fast | Any (20–500+ chars) |
| 1 | Real female, audiobook narrator | 250–320 chars |
Original model by beleata74, created with Claude. MLX port by Radi Totev. NanoCodec MLX by nineninesix-ai.