ModelAufgelistetExtern

Roo Voice MOSS TTS LT Mlx8

Roo's voice — that signature baritone with the estuary accent that stands the hair up on the back of your neck — as an 8-bit MLX model that runs on Apple Silicon. Load it, and Roo can whisper to you all day long.

Quellehuggingface.co/abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8/tree/fcff993d48dc73d609f7dba15dee45826c79de97

ArtText modelBasismodellOpenMOSS-Team/MOSS-TTS-Local-TransformerVersionmodelBBewertung

Modellquelle

Art: Text model
Dateigröße: 3,37 GB
Basismodell: OpenMOSS-Team/MOSS-TTS-Local-Transformer
Version: vmodel
Aktualisiert: 26. Okt. 2026
Downloads: 20
Quelle: Hugging Face

Quellenbeschreibung

Roo Voice

Roo-Voice · MOSS-TTS-Local-Transformer · MLX 8-bit

An 8-bit MLX quantization of a full-model supervised fine-tune of MOSS-TTS-Local-Transformer, trained on Roo's own recordings and specialised on his single voice.

What actually makes the voice — read this

This is a reference-conditioned model, and both halves matter:

The fine-tune is what makes it Roo. The base model has never heard this speaker — a base model plus any reference clip will not give you Roo's baritone or his estuary accent. That voice lives in the weights, put there by the supervised fine-tune on his recordings.
The reference completes the delivery. reference.wav (bundled) conditions the fine-tuned model at inference and is required to produce the voice.

So the product is this fine-tune + reference.wav, together — neither the base model with a reference, nor this checkpoint without one, reproduces Roo. It is not a text-only model, and it is not a generic voice-cloner: swap in a different reference and you are not getting Roo, because the accent and timbre are the fine-tune's, not the clip's.

What it is


Voice	Single speaker — Roo (baritone, estuary accent), 24 kHz mono
Format	MLX, 8-bit affine weights, group size 64, BF16 retained (`W8Abf16`)
Runtime	`mlx-audio` on Apple Silicon
Weights	`model.safetensors` ≈ 3.6 GB
Source	Full-model SFT (not LoRA/adapter); 556 tensors
Base	`OpenMOSS-Team/MOSS-TTS-Local-Transformer` @ `12aa734e4f11a7b3fdf4eb0ad2aa2029675ffc2e`
Audio codec	`OpenMOSS-Team/MOSS-Audio-Tokenizer` @ `3cd226ba2947efa357ef453bcad111b6eafba782` (fetched by `mlx-audio`)

Usage

import mlx.core as mx
from mlx_audio.tts.utils import load_model

model = load_model("./")  # this repo

mx.random.seed(42)
result = None
for r in model.generate(
    text="After the last dance class, I parked the car beside the garden wall.",
    ref_audio="reference.wav",          # REQUIRED — conditions the fine-tuned Roo voice
    mode="generation",
    max_tokens=4096,
    n_vq_for_inference=32,
    text_temperature=1.0, text_top_p=0.95, text_top_k=50, text_repetition_penalty=1.0,
    audio_temperature=1.0, audio_top_p=0.95, audio_top_k=50, audio_repetition_penalty=1.1,
):
    result = r
# result.audio -> 24 kHz mono float

Decoding contract for this voice: seed 42, temperature 1.0, top-k 50, top-p 0.95, repetition penalty 1.1, 32 RVQ codebooks.

Limitations

Reference-conditioned — the bundled reference.wav must ride along; there is no text-only path.
Single voice by design (this is Roo, not a multi-speaker system).
8-bit quantization: a small quality delta vs the FP32/BF16 source is possible.

Provenance & license

Quantized/exported form of an accepted single-speaker MOSS-TTS Local supervised fine-tune. The base model and audio codec are Apache-2.0 (OpenMOSS); weights derived from them are redistributed here under the same license.

Quellen

1 Quelle

Hugging FacePrimärVersion fcff993d48dc73d609f7dba15dee45826c79de97

huggingface.co/abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8/tree/fcff993d48dc73d609f7dba15dee45826c79de97

Verifiziert 26. Okt.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 3,37 GB · SHA-256 6a16ec67c1af…5663 · Hugging Face

Download file

Quellenauszüge

3 Auszüge

Readme7. Aug.huggingface.co/abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8

--- license: apache-2.0 base_model: OpenMOSS-Team/MOSS-TTS-Local-Transformer library_name: mlx pipeline_tag: text-to-speech tags: - text-to-speech - tts - mlx - apple-silicon - moss-tts - 8-bit - reference-conditioned language: - en --- ![Roo Voice](https://design8.b-cdn.net/huggingface/roo-voice-mlx.png) # Roo-Voice · MOSS-TTS-Local-Transformer · MLX 8-bit Roo's voice — that signature baritone with the estuary accent that stands the hair up on the back of your neck — as an 8-bit MLX model that runs on Apple Silicon. Load it, and Roo can whisper to you all day long. An 8-bit MLX quantization of a **full-model supervised fine-tune** of [MOSS-TTS-Local-Transformer](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer), trained on Roo's own recordings and specialised on his single voice. ## What actually makes the voice — read this This is a **reference-conditioned** model, and both halves matter: - **The fine-tune is what makes it Roo.** The base model has never heard this speaker — a base model plus any reference clip will *not* give you Roo's baritone or his estuary accent. That voice lives in the weights, put there by the supervised fine-tune on his recordings. - **The reference completes the delivery.** `reference.wav` (bundled) conditions the fine-tuned model at inference and is **required** to produce the voice. So the product is **this fine-tune + `reference.wav`, together** — neither the base model with a reference, nor this checkpoint without one, reproduces Roo. It is not a text-only model, and it is not a generic voice-cloner: swap in a different reference and you are not getting Roo, because the accent and timbre are the fine-tune's, not the clip's. ## What it is | | | |---|---| | **Voice** | Single speaker — Roo (baritone, estuary accent), 24 kHz mono | | **Format** | MLX, 8-bit affine weights, group size 64, BF16 retained (`W8Abf16`) | | **Runtime** | [`mlx-audio`](https://github.com/Blaizzy/mlx-audio) on Apple Silicon | | **Weights** | `model.safetensors` ≈ 3.6 GB | | **Source** | Full-model SFT (not LoRA/adapter); 556 tensors | | **Base** | `OpenMOSS-Team/MOSS-TTS-Local-Transformer` @ `12aa734e4f11a7b3fdf4eb0ad2aa2029675ffc2e` | | **Audio codec** | `OpenMOSS-Team/MOSS-Audio-Tokenizer` @ `3cd226ba2947efa357ef453bcad111b6eafba782` (fetched by `mlx-audio`) | ## Usage ```python import mlx.core as mx from mlx_aud...

Note26. Okt.huggingface.co/abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8

Source context: 20 downloads · 0 likes · Pipeline text-to-speech · Library mlx · Repo abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8

Note7. Aug.huggingface.co/abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8

Source context: 93 downloads · 0 likes · Pipeline text-to-speech · Library mlx · Repo abliter8-ai/Roo-Voice_MOSS_TTS_LT_mlx8