Improve model card metadata and add paper link

This pull request improves the model card for the MOSS-TTS Family by:
- Adding `library_name: transformers` metadata, as the model is compatible with the Transformers library via `AutoModel`.
- Adding `pipeline_tag: text-to-speech` to improve model discoverability.
- Linking the repository to the official research paper: [MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models](https://huggingface.co/papers/2602.10934).
- Including a sample usage code snippet for audio reconstruction directly from the official GitHub documentation.

README.md

@@ -1,7 +1,4 @@
 ---
-license: apache-2.0
-tags:
-- text-to-speech
 language:
 - zh
 - en
@@ -23,7 +20,15 @@ language:
 - hu
 - el
 - tr
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-to-speech
+tags:
+- text-to-speech
+- audio-tokenizer
+- moss
 ---
+
 # MOSS-TTS Family
 
 <br>
@@ -36,10 +41,10 @@ language:
 
 
 <div align="center">
-  <a href="https://github.com/OpenMOSS/MOSS-TTS/tree/main"><img src="https://img.shields.io/badge/Project%20Page-GitHub-blue"></a>
+  <a href="https://github.com/OpenMOSS/MOSS-Audio-Tokenizer"><img src="https://img.shields.io/badge/Project%20Page-GitHub-blue"></a>
   <a href="https://modelscope.cn/collections/OpenMOSS-Team/MOSS-TTS"><img src="https://img.shields.io/badge/ModelScope-Models-lightgrey?logo=modelscope&amp"></a>
   <a href="https://mosi.cn/#models"><img src="https://img.shields.io/badge/Blog-View-blue?logo=internet-explorer&amp"></a>
-  <a href="https://github.com/OpenMOSS/MOSS-TTS"><img src="https://img.shields.io/badge/Arxiv-Coming%20soon-red?logo=arxiv&amp"></a>
+  <a href="https://huggingface.co/papers/2602.10934"><img src="https://img.shields.io/badge/Arxiv-2602.10934-red?logo=arxiv&amp"></a>
 
   <a href="https://studio.mosi.cn"><img src="https://img.shields.io/badge/AIStudio-Try-green?logo=internet-explorer&amp"></a>
   <a href="https://studio.mosi.cn/docs/moss-tts"><img src="https://img.shields.io/badge/API-Docs-00A3FF?logo=fastapi&amp"></a>
@@ -48,622 +53,87 @@ language:
 </div>
 
 ## Overview
-MOSS‑TTS Family is an open‑source **speech and sound generation model family** from [MOSI.AI](https://mosi.cn/#hero) and the [OpenMOSS team](https://www.open-moss.com/). 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 sound effects, and real‑time streaming TTS.
-
-
-## Introduction
-
-<p align="center">
-  <img src="https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_imgaes_demo/moss_tts_family_arch.jpeg" width="85%" />
-</p>
-
-
-When a single piece of audio needs to **sound like a real person**, **pronounce every word accurately**, **switch speaking styles across content**, **remain stable over tens of minutes**, and **support dialogue, role‑play, and real‑time interaction**, a single TTS model is often not enough. The **MOSS‑TTS Family** breaks the workflow into five production‑ready models that can be used independently or composed into a complete pipeline.
-
-- **MOSS‑TTS**: MOSS-TTS is the flagship production TTS foundation model, centered on high-fidelity zero-shot voice cloning with controllable long-form synthesis, pronunciation, and multilingual/code-switched speech. It serves as the core engine for scalable narration, dubbing, and voice-driven products.
-- **MOSS‑TTSD**: MOSS-TTSD is a production long-form dialogue model for expressive multi-speaker conversational audio at scale. It supports long-duration continuity, turn-taking control, and zero-shot voice cloning from short references for podcasts, audiobooks, commentary, dubbing, and entertainment dialogue.
-- **MOSS‑VoiceGenerator**: MOSS-VoiceGenerator is an open-source voice design model that creates speaker timbres directly from free-form text, without reference audio. It unifies timbre design, style control, and content synthesis, and can be used standalone or as a voice-design layer for downstream TTS.
-- **MOSS‑SoundEffect**: MOSS-SoundEffect is a high-fidelity text-to-sound model with broad category coverage and controllable duration for real content production. It generates stable audio from prompts across ambience, urban scenes, creatures, human actions, and music-like clips for film, games, interactive media, and data synthesis.
-- **MOSS‑TTS‑Realtime**: MOSS-TTS-Realtime is a context-aware, multi-turn streaming TTS model for real-time voice agents. By conditioning on dialogue history across both text and prior user acoustics, it delivers low-latency synthesis with coherent, consistent voice responses across turns.
-
-
-## Released Models
-
-| Model | Architecture | Size | Model Card | Hugging Face |
-|---|---|---:|---|---|
-| **MOSS-TTS** | MossTTSDelay | 8B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS) |
-|  | MossTTSLocal | 1.7B | [moss_tts_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer) |
-| **MOSS‑TTSD‑V1.0** | MossTTSDelay | 8B | [moss_ttsd_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_ttsd_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTSD-v1.0) |
-| **MOSS‑VoiceGenerator** | MossTTSDelay | 1.7B | [moss_voice_generator_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_voice_generator_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-Voice-Generator) |
-| **MOSS‑SoundEffect** | MossTTSDelay | 8B | [moss_sound_effect_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_sound_effect_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-SoundEffect) |
-| **MOSS‑TTS‑Realtime** | MossTTSRealtime | 1.7B | [moss_tts_realtime_model_card.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/docs/moss_tts_realtime_model_card.md) | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Realtime) |
-
-## Supported Languages
-
-MOSS-TTS, MOSS-TTSD and MOSS-TTS-Realtime currently supports **20 languages**:
-
-| Language | Code | Flag | Language | Code | Flag | Language | Code | Flag |
-|---|---|---|---|---|---|---|---|---|
-| Chinese | zh | 🇨🇳 | English | en | 🇺🇸 | German | de | 🇩🇪 |
-| Spanish | es | 🇪🇸 | French | fr | 🇫🇷 | Japanese | ja | 🇯🇵 |
-| Italian | it | 🇮🇹 | Hebrew | he | 🇮🇱 | Korean | ko | 🇰🇷 |
-| Russian | ru | 🇷🇺 | Persian (Farsi) | fa | 🇮🇷 | Arabic | ar | 🇸🇦 |
-| Polish | pl | 🇵🇱 | Portuguese | pt | 🇵🇹 | Czech | cs | 🇨🇿 |
-| Danish | da | 🇩🇰 | Swedish | sv | 🇸🇪 | Hungarian | hu | 🇭🇺 |
-| Greek | el | 🇬🇷 | Turkish | tr | 🇹🇷 |  |  |  |
-
-
-# MOSS-TTS
-## 1. Overview
-### 1.1 TTS Family Positioning
-MOSS-TTS is the **flagship base model** in our open-source **TTS Family**. It is designed as a production-ready synthesis backbone that can serve as the primary high-quality engine for scalable voice applications, and as a strong research baseline for controllable TTS and discrete audio token modeling.
-
-**Design goals**
-- **Production readiness**: robust voice cloning with stable, on-brand speaker identity at scale
-- **Controllability**: duration and pronunciation controls that integrate into real workflows
-- **Long-form stability**: consistent identity and delivery for extended narration
-- **Multilingual coverage**: multilingual and code-switched synthesis as first-class capabilities
-
-
-
-### 1.2 Key Capabilities
-
-MOSS-TTS delivers state-of-the-art quality while providing the fine-grained controllability and long-form stability required for production-grade voice applications, from zero-shot cloning and hour-long narration to token- and phoneme-level control across multilingual and code-switched speech.
-
-* **State-of-the-art evaluation performance** — top-tier objective and subjective results across standard TTS benchmarks and in-house human preference testing, validating both fidelity and naturalness.
-* **Zero-shot Voice Cloning (Voice Clone)** — clone a target speaker’s timbre (and part of speaking style) from short reference audio, without speaker-specific fine-tuning.
-* **Ultra-long Speech Generation (up to 1 hour)** — support continuous long-form speech generation for up to one hour in a single run, designed for extended narration and long-session content creation.
-* **Token-level Duration Control** — control pacing, rhythm, pauses, and speaking rate at token resolution for precise alignment and expressive delivery.
-* **Phoneme-level Pronunciation Control** — supports:
-
-  * pure **Pinyin** input
-  * pure **IPA** phoneme input
-  * mixed **Chinese / English / Pinyin / IPA** input in any combination
-* **Multilingual support** — high-quality multilingual synthesis with robust generalization across languages and accents.
-* **Code-switching** — natural mixed-language generation within a single utterance (e.g., Chinese–English), with smooth transitions, consistent speaker identity, and pronunciation-aware rendering on both sides of the switch.
-
-
-
-### 1.3 Model Architecture
-
-MOSS-TTS includes **two complementary architectures**, both trained and released to explore different performance/latency tradeoffs and to support downstream research.
-
-**Architecture A: Delay Pattern (MossTTSDelay)**
-- Single Transformer backbone with **(n_vq + 1) heads**.
-- Uses **delay scheduling** for multi-codebook audio tokens.
-- Strong long-context stability, efficient inference, and production-friendly behavior.
+MOSS‑TTS Family is an open‑source **speech and sound generation model family** from [MOSI.AI](https://mosi.cn/#hero) and the [OpenMOSS team](https://www.open-moss.com/). It is built upon the **MOSS-Audio-Tokenizer**, a unified discrete audio tokenizer based on the **CAT** (Causal Audio Tokenizer with Transformer) architecture presented in the paper [MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models](https://huggingface.co/papers/2602.10934).
 
-**Architecture B: Global Latent + Local Transformer (MossTTSLocal)**
-- Backbone produces a **global latent** per time step.
-- A lightweight **Local Transformer** emits a token block per step.
-- **Streaming-friendly** with simpler alignment (no delay scheduling).
+## Sample Usage (Audio Reconstruction)
 
-**Why train both?**
-- **Exploration of architectural potential** and validation across multiple generation paradigms.
-- **Different tradeoffs**: Delay pattern tends to be faster and more stable for long-form synthesis; Local is smaller and excels on objective benchmarks.
-- **Open-source value**: two strong baselines for research, ablation, and downstream innovation.
-
-For full details, see:
-- **[moss_tts_delay/README.md](https://github.com/OpenMOSS/MOSS-TTS/blob/main/moss_tts_delay/README.md)**
-- **[moss_tts_local/README.md](https://github.com/OpenMOSS/MOSS-TTS/tree/main/moss_tts_local)**
-
-
-
-### 1.4 Released Models
-
-| Model | Description |
-|---|---|
-| **MossTTSDelay-8B** | **Recommended for production**. Faster inference, stronger long-context stability, and robust voice cloning quality. Best for large-scale deployment and long-form narration. |
-| **MossTTSLocal-1.7B** | **Recommended for evaluation and research**. Smaller model size with SOTA objective metrics. Great for quick experiments, ablations, and academic studies. |
-
-**Recommended decoding hyperparameters (per model)**
-
-| Model | audio_temperature | audio_top_p | audio_top_k | audio_repetition_penalty |
-|---|---:|---:|---:|---:|
-| **MOSS-TTSDelay-8B** | 1.7 | 0.8 | 25 | 1.0 |
-| **MOSS-TTSLocal-1.7B** | 1.0 | 0.95 | 50 | 1.1 |
-
-> Note: `max_new_tokens` controls duration. At 12.5 tokens per second, **1s ≈ 12.5 tokens**.
-
-
-
-## 2. Quick Start
-
-
-
-### Environment Setup
-
-We recommend a clean, isolated Python environment with **Transformers 5.0.0** to avoid dependency conflicts.
-
-```bash
-conda create -n moss-tts python=3.12 -y
-conda activate moss-tts
-```
-
-Install all required dependencies:
-
-```bash
-git clone https://github.com/OpenMOSS/MOSS-TTS.git
-cd MOSS-TTS
-pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e .
-```
-
-#### (Optional) Install FlashAttention 2
-
-For better speed and lower GPU memory usage, you can install FlashAttention 2 if your hardware supports it.
-
-```bash
-pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"
-```
-
-If your machine has limited RAM and many CPU cores, you can cap build parallelism:
-
-```bash
-MAX_JOBS=4 pip install --extra-index-url https://download.pytorch.org/whl/cu128 -e ".[flash-attn]"
-```
-
-Notes:
-- Dependencies are managed in `pyproject.toml`, which currently pins `torch==2.9.1+cu128` and `torchaudio==2.9.1+cu128`.
-- If FlashAttention 2 fails to build on your machine, you can skip it and use the default attention backend.
-- FlashAttention 2 is only available on supported GPUs and is typically used with `torch.float16` or `torch.bfloat16`.
-
-
-### Basic Usage
-
-
-> Tip: For evaluation and research purposes, we recommend using **MOSS-TTSLocal-1.7B**. 
-
-MOSS-TTS provides a convenient `generate` interface for rapid usage. The examples below cover:
-1. Direct generation (Chinese / English / Pinyin / IPA)
-2. Voice cloning
-3. Duration control
+The tokenizer can be used to compress audio into discrete tokens and reconstruct it back into waveforms.
 
 ```python
-import importlib.util
-from pathlib import Path
 import torch
+from transformers import AutoModel
 import torchaudio
-from transformers import AutoModel, AutoProcessor, GenerationConfig
-# Disable the broken cuDNN SDPA backend
-torch.backends.cuda.enable_cudnn_sdp(False)
-# Keep these enabled as fallbacks
-torch.backends.cuda.enable_flash_sdp(True)
-torch.backends.cuda.enable_mem_efficient_sdp(True)
-torch.backends.cuda.enable_math_sdp(True)
-
-class DelayGenerationConfig(GenerationConfig):
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
-        self.layers = kwargs.get("layers", [{} for _ in range(32)])
-        self.do_samples = kwargs.get("do_samples", None)
-        self.n_vq_for_inference = 32
-        
-def initial_config(tokenizer, model_name_or_path):
-    generation_config = DelayGenerationConfig.from_pretrained(model_name_or_path)
-    generation_config.pad_token_id = tokenizer.pad_token_id
-    generation_config.eos_token_id = 151653
-    generation_config.max_new_tokens = 1000000
-    generation_config.temperature = 1.0
-    generation_config.top_p = 0.95
-    generation_config.top_k = 100
-    generation_config.repetition_penalty = 1.1
-    generation_config.use_cache = True
-    generation_config.do_sample = False
-    return generation_config
-
-
-pretrained_model_name_or_path = "OpenMOSS-Team/MOSS-TTS-Local-Transformer"
-device = "cuda" if torch.cuda.is_available() else "cpu"
-dtype = torch.bfloat16 if device == "cuda" else torch.float32
-
-def resolve_attn_implementation() -> str:
-    # Prefer FlashAttention 2 when package + device conditions are met.
-    if (
-        device == "cuda"
-        and importlib.util.find_spec("flash_attn") is not None
-        and dtype in {torch.float16, torch.bfloat16}
-    ):
-        major, _ = torch.cuda.get_device_capability()
-        if major >= 8:
-            return "flash_attention_2"
-
-    # CUDA fallback: use PyTorch SDPA kernels.
-    if device == "cuda":
-        return "sdpa"
 
-    # CPU fallback.
-    return "eager"
+repo_id = "OpenMOSS-Team/MOSS-Audio-Tokenizer"
+model = AutoModel.from_pretrained(repo_id, trust_remote_code=True).eval()
 
+# Load and resample audio
+wav, sr = torchaudio.load('path_to_audio.wav')
+if sr != model.sampling_rate:
+    wav = torchaudio.functional.resample(wav, sr, model.sampling_rate)
+wav = wav.unsqueeze(0)
 
-attn_implementation = resolve_attn_implementation()
-print(f"[INFO] Using attn_implementation={attn_implementation}")
+# Encode audio to tokens
+enc = model.encode(wav, return_dict=True)
+print(f"enc.audio_codes.shape: {enc.audio_codes.shape}")
 
-processor = AutoProcessor.from_pretrained(
-    pretrained_model_name_or_path,
-    trust_remote_code=True,
-)
-processor.audio_tokenizer = processor.audio_tokenizer.to(device)
-
-text_1 = """亲爱的你，
-你好呀。
-
-今天，我想用最认真、最温柔的声音，对你说一些重要的话。
-这些话，像一颗小小的星星，希望能在你的心里慢慢发光。
-
-首先，我想祝你——
-每天都能平平安安、快快乐乐。
-
-希望你早上醒来的时候，
-窗外有光，屋子里很安静，
-你的心是轻轻的，没有着急，也没有害怕。
-"""
-text_2 = """We stand on the threshold of the AI era.
-Artificial intelligence is no longer just a concept in laboratories, but is entering every industry, every creative endeavor, and every decision. It has learned to see, hear, speak, and think, and is beginning to become an extension of human capabilities. AI is not about replacing humans, but about amplifying human creativity, making knowledge more equitable, more efficient, and allowing imagination to reach further. A new era, jointly shaped by humans and intelligent systems, has arrived."""
-text_3 = "nin2 hao3，qing3 wen4 nin2 lai2 zi4 na3 zuo4 cheng2 shi4？"
-text_4 = "nin2 hao3，qing4 wen3 nin2 lai2 zi4 na4 zuo3 cheng4 shi3？"
-text_5 = "您好，请问您来自哪 zuo4 cheng2 shi4？"
-text_6 = "/həloʊ, meɪ aɪ æsk wɪtʃ sɪti juː ɑːr frʌm?/"
-
-# Use audio from ./assets/audio to avoid downloading from the cloud.
-ref_audio_1 = "https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_demo/reference_zh.wav"
-ref_audio_2 = "https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_demo/reference_en.m4a"
-
-conversations = [
-    # Direct TTS (no reference)
-    [
-        processor.build_user_message(text=text_1)
-    ],
-    [
-        processor.build_user_message(text=text_2)
-    ],
-    # Pinyin or IPA input
-    [
-        processor.build_user_message(text=text_3)
-    ],
-    [
-        processor.build_user_message(text=text_4)
-    ],
-    [
-        processor.build_user_message(text=text_5)
-    ],
-    [
-        processor.build_user_message(text=text_6)
-    ],
-    # Voice cloning (with reference)
-    [
-        processor.build_user_message(text=text_1, reference=[ref_audio_1])
-    ],
-    [
-        processor.build_user_message(text=text_2, reference=[ref_audio_2])
-    ],
-]
-
-model = AutoModel.from_pretrained(
-    pretrained_model_name_or_path,
-    trust_remote_code=True,
-    attn_implementation=attn_implementation,
-    torch_dtype=dtype,
-).to(device)
-model.eval()
-
-generation_config = initial_config(processor.tokenizer, pretrained_model_name_or_path)
-generation_config.n_vq_for_inference = model.channels - 1
-generation_config.do_samples = [True] * model.channels
-generation_config.layers = [
-    {
-        "repetition_penalty": 1.0, 
-        "temperature": 1.5, 
-        "top_p": 1.0, 
-        "top_k": 50
-    }
-] + [ 
-    {
-        "repetition_penalty": 1.1, 
-        "temperature": 1.0, 
-        "top_p": 0.95,
-        "top_k": 50
-    }
-] * (model.channels - 1) 
-
-batch_size = 1
-
-save_dir = Path(f"inference_root_moss_tts_local_transformer_generation")
-save_dir.mkdir(exist_ok=True, parents=True)
-sample_idx = 0
-with torch.no_grad():
-    for start in range(0, len(conversations), batch_size):
-        batch_conversations = conversations[start : start + batch_size]
-        batch = processor(batch_conversations, mode="generation")
-        input_ids = batch["input_ids"].to(device)
-        attention_mask = batch["attention_mask"].to(device)
-
-        outputs = model.generate(
-            input_ids=input_ids,
-            attention_mask=attention_mask,
-            generation_config=generation_config
-        )
-
-        for message in processor.decode(outputs):
-            audio = message.audio_codes_list[0]
-            out_path = save_dir / f"sample{sample_idx}.wav"
-            sample_idx += 1
-            torchaudio.save(out_path, audio.unsqueeze(0), processor.model_config.sampling_rate)
+# Decode tokens back to audio
+dec = model.decode(enc.audio_codes, return_dict=True)
+print(f"dec.audio.shape: {dec.audio.shape}")
 
+wav_rec = dec.audio.squeeze(0)
+torchaudio.save("reconstructed.wav", wav_rec, sample_rate=model.sampling_rate)
 ```
 
-### Continuation + Voice Cloning (Prefix Audio + Text)
-
-MOSS-TTS supports continuation-based cloning: provide a prefix audio clip in the assistant message, and make sure the **prefix transcript** is included in the text. The model continues in the same speaker identity and style.
-
-```python
-import importlib.util
-from pathlib import Path
-import torch
-import torchaudio
-from transformers import AutoModel, AutoProcessor, GenerationConfig
-# Disable the broken cuDNN SDPA backend
-torch.backends.cuda.enable_cudnn_sdp(False)
-# Keep these enabled as fallbacks
-torch.backends.cuda.enable_flash_sdp(True)
-torch.backends.cuda.enable_mem_efficient_sdp(True)
-torch.backends.cuda.enable_math_sdp(True)
-
-class DelayGenerationConfig(GenerationConfig):
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
-        self.layers = kwargs.get("layers", [{} for _ in range(32)])
-        self.do_samples = kwargs.get("do_samples", None)
-        self.n_vq_for_inference = 32
-        
-def initial_config(tokenizer, model_name_or_path):
-    generation_config = DelayGenerationConfig.from_pretrained(model_name_or_path)
-    generation_config.pad_token_id = tokenizer.pad_token_id
-    generation_config.eos_token_id = 151653
-    generation_config.max_new_tokens = 1000000
-    generation_config.temperature = 1.0
-    generation_config.top_p = 0.95
-    generation_config.top_k = 100
-    generation_config.repetition_penalty = 1.1
-    generation_config.use_cache = True
-    generation_config.do_sample = False
-    return generation_config
-
-
-pretrained_model_name_or_path = "OpenMOSS-Team/MOSS-TTS-Local-Transformer"
-device = "cuda" if torch.cuda.is_available() else "cpu"
-dtype = torch.bfloat16 if device == "cuda" else torch.float32
-
-def resolve_attn_implementation() -> str:
-    # Prefer FlashAttention 2 when package + device conditions are met.
-    if (
-        device == "cuda"
-        and importlib.util.find_spec("flash_attn") is not None
-        and dtype in {torch.float16, torch.bfloat16}
-    ):
-        major, _ = torch.cuda.get_device_capability()
-        if major >= 8:
-            return "flash_attention_2"
-
-    # CUDA fallback: use PyTorch SDPA kernels.
-    if device == "cuda":
-        return "sdpa"
-
-    # CPU fallback.
-    return "eager"
-
-
-attn_implementation = resolve_attn_implementation()
-print(f"[INFO] Using attn_implementation={attn_implementation}")
-
-processor = AutoProcessor.from_pretrained(
-    pretrained_model_name_or_path,
-    trust_remote_code=True,
-)
-processor.audio_tokenizer = processor.audio_tokenizer.to(device)
-
-text_1 = """亲爱的你，
-你好呀。
-
-今天，我想用最认真、最温柔的声音，对你说一些重要的话。
-这些话，像一颗小小的星星，希望能在你的心里慢慢发光。
-
-首先，我想祝你——
-每天都能平平安安、快快乐乐。
-
-希望你早上醒来的时候，
-窗外有光，屋子里很安静，
-你的心是轻轻的，没有着急，也没有害怕。
-"""
-
-ref_text_1 = "太阳系八大行星之一。"
-# Use audio from ./assets/audio to avoid downloading from the cloud.
-ref_audio_1 = "https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_demo/reference_zh.wav"
-
-conversations = [
-    # Continuatoin only
-    [
-        processor.build_user_message(text=ref_text_1 + text_1),
-        processor.build_assistant_message(audio_codes_list=[ref_audio_1])
-    ],
-]
-
-model = AutoModel.from_pretrained(
-    pretrained_model_name_or_path,
-    trust_remote_code=True,
-    attn_implementation=attn_implementation,
-    torch_dtype=dtype,
-).to(device)
-model.eval()
-
-generation_config = initial_config(processor.tokenizer, pretrained_model_name_or_path)
-generation_config.n_vq_for_inference = model.channels - 1
-generation_config.do_samples = [True] * model.channels
-generation_config.layers = [
-    {
-        "repetition_penalty": 1.0, 
-        "temperature": 1.5, 
-        "top_p": 1.0, 
-        "top_k": 50
-    }
-] + [ 
-    {
-        "repetition_penalty": 1.1, 
-        "temperature": 1.0, 
-        "top_p": 0.95,
-        "top_k": 50
-    }
-] * (model.channels - 1) 
-
-batch_size = 1
-
-save_dir = Path("inference_root_moss_tts_local_transformer_continuation")
-save_dir.mkdir(exist_ok=True, parents=True)
-sample_idx = 0
-with torch.no_grad():
-    for start in range(0, len(conversations), batch_size):
-        batch_conversations = conversations[start : start + batch_size]
-        batch = processor(batch_conversations, mode="continuation")
-        input_ids = batch["input_ids"].to(device)
-        attention_mask = batch["attention_mask"].to(device)
-
-        outputs = model.generate(
-            input_ids=input_ids,
-            attention_mask=attention_mask,
-            generation_config=generation_config
-        )
-
-        for message in processor.decode(outputs):
-            audio = message.audio_codes_list[0]
-            out_path = save_dir / f"sample{sample_idx}.wav"
-            sample_idx += 1
-            torchaudio.save(out_path, audio.unsqueeze(0), processor.model_config.sampling_rate)
-
-```
+## Introduction
 
+<p align="center">
+  <img src="https://speech-demo.oss-cn-shanghai.aliyuncs.com/moss_tts_demo/tts_readme_imgaes_demo/moss_tts_family_arch.jpeg" width="85%" />
+</p>
 
 
-### Input Types
+When a single piece of audio needs to **sound like a real person**, **pronounce every word accurately**, **switch speaking styles across content**, **remain stable over tens of minutes**, and **support dialogue, role‑play, and real‑time interaction**, a single TTS model is often not enough. The **MOSS‑TTS Family** breaks the workflow into five production‑ready models that can be used independently or composed into a complete pipeline.
 
-**UserMessage**
+- **MOSS‑TTS**: MOSS-TTS is the flagship production TTS foundation model, centered on high-fidelity zero-shot voice cloning with controllable long-form synthesis, pronunciation, and multilingual/code-switched speech.
+- **MOSS‑TTSD**: MOSS-TTSD is a production long-form dialogue model for expressive multi-speaker conversational audio at scale.
+- **MOSS‑VoiceGenerator**: MOSS-VoiceGenerator is an open-source voice design model that creates speaker timbres directly from free-form text.
+- **MOSS‑SoundEffect**: MOSS-SoundEffect is a high-fidelity text-to-sound model with broad category coverage and controllable duration.
+- **MOSS‑TTS‑Realtime**: MOSS-TTS-Realtime is a context-aware, multi-turn streaming TTS model for real-time voice agents.
 
-| Field | Type | Required | Description |
-|---|---|---:|---|
-| `text` | `str` | Yes | Text to synthesize. Supports Chinese, English, German, French, Spanish, Japanese, Korean, etc. Can mix raw text with Pinyin or IPA for pronunciation control. |
-| `reference` | `List[str]` | No | Reference audio for voice cloning. For current MOSS-TTS, **one audio** is expected in the list. |
-| `tokens` | `int` | No | Expected number of audio tokens. **1s ≈ 12.5 tokens**. |
 
-**AssistantMessage**
+## Released Models
 
-| Field | Type | Required | Description |
+| Model | Architecture | Size | Hugging Face |
 |---|---|---:|---|
-| `audio_codes_list` | `List[str]` | Only for continuation | Prefix audio for continuation-based cloning. Use audio file paths or URLs. |
-
-
-
-### Generation Hyperparameters (MOSS-TTS-Local)
-
-MOSS-TTSLocal utilizes `DelayGenerationConfig` to manage hierarchical sampling. Due to the **Progressive Sequence Dropout** training mechanism, the model supports variable bitrate inference by adjusting the RVQ depth.
-
-| Parameter | Type | Recommended (Audio Layers) | Description |
-| :--- | :--- | :---: | :--- |
-| `max_new_tokens` | `int` | — | Controls total generated audio tokens. **1s ≈ 12.5 tokens**. |
-| `n_vq_for_inference` | `int` | 32 | **RVQ Inference Depth**: Controls the number of codebook layers generated. Higher values (max 32) improve audio fidelity but slow down inference; lower values speed up inference but reduce audio quality. |
-| `audio_temperature` | `float` | 1.0 | Temperature for audio token layers (Layer 1+). Lower values ensure more stable and consistent acoustic reconstruction. |
-| `audio_top_p` | `float` | 0.95 | Nucleus sampling cutoff for audio layers. |
-| `audio_top_k` | `int` | 50 | Top-K sampling filter for audio layers. |
-| `audio_repetition_penalty` | `float` | 1.1 | Discourages repeating acoustic patterns. Values > 1.0 help prevent artifacts in long-form synthesis. |
-
-
-
-### Pinyin Input
-
-Use tone-numbered Pinyin such as `ni3 hao3 wo3 men1`. You can convert Chinese text with [pypinyin](https://github.com/mozillazg/python-pinyin), then adjust tones for pronunciation control.
-
-```python
-import re
-from pypinyin import pinyin, Style
-
-CN_PUNCT = r"，。！？；：、（）“”‘’"
-
-
-def fix_punctuation_spacing(s: str) -> str:
-    s = re.sub(rf"\s+([{CN_PUNCT}])", r"\1", s)
-    s = re.sub(rf"([{CN_PUNCT}])\s+", r"\1", s)
-    return s
-
-
-def zh_to_pinyin_tone3(text: str, strict: bool = True) -> str:
-    result = pinyin(
-        text,
-        style=Style.TONE3,
-        heteronym=False,
-        strict=strict,
-        errors="default",
-    )
-
-    s = " ".join(item[0] for item in result)
-    return fix_punctuation_spacing(s)
-
-text = zh_to_pinyin_tone3("您好，请问您来自哪座城市？")
-print(text)
-
-# Expected: nin2 hao3，qing3 wen4 nin2 lai2 zi4 na3 zuo4 cheng2 shi4？
-# Try: nin2 hao3，qing4 wen3 nin2 lai2 zi4 na4 zuo3 cheng4 shi3？
-```
-
-
-
-### IPA Input
-
-Use `/.../` to wrap IPA sequences so they are distinct from normal text. You can use [DeepPhonemizer](https://github.com/spring-media/DeepPhonemizer) to convert English paragraphs or words into IPA sequences.
-
-```python
-from dp.phonemizer import Phonemizer
-
-# Download a phonemizer checkpoint from https://public-asai-dl-models.s3.eu-central-1.amazonaws.com/DeepPhonemizer/en_us_cmudict_ipa_forward.pt
-model_path = "<path-to-phonemizer-checkpoint>"
-phonemizer = Phonemizer.from_checkpoint(model_path)
-
-english_texts = "Hello, may I ask which city you are from?"
-phoneme_outputs = phonemizer(
-    english_texts,
-    lang="en_us",
-    batch_size=8
-)
-model_input_text = f"/{phoneme_outputs}/"
-print(model_input_text)
-
-# Expected: /həloʊ, meɪ aɪ æsk wɪtʃ sɪti juː ɑːr frʌm?/
-```
+| **MOSS-TTS** | MossTTSDelay | 8B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS) |
+|  | MossTTSLocal | 1.7B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Local-Transformer) |
+| **MOSS‑TTSD‑V1.0** | MossTTSDelay | 8B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTSD-v1.0) |
+| **MOSS‑VoiceGenerator** | MossTTSDelay | 1.7B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-Voice-Generator) |
+| **MOSS‑SoundEffect** | MossTTSDelay | 8B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-SoundEffect) |
+| **MOSS‑TTS‑Realtime** | MossTTSRealtime | 1.7B | 🤗 [Huggingface](https://huggingface.co/OpenMOSS-Team/MOSS-TTS-Realtime) |
 
+## Supported Languages
 
+MOSS-TTS, MOSS-TTSD and MOSS-TTS-Realtime currently supports **20 languages**: Chinese, English, German, Spanish, French, Japanese, Italian, Hebrew, Korean, Russian, Persian (Farsi), Arabic, Polish, Portuguese, Czech, Danish, Swedish, Hungarian, Greek, and Turkish.
 
-## 3. Evaluation
-MOSS-TTS achieved state-of-the-art results on the open-source zero-shot TTS benchmark Seed-TTS-eval, not only surpassing all open-source models but also rivaling the most powerful closed-source models.
+## Evaluation
+MOSS-TTS achieved state-of-the-art results on the zero-shot TTS benchmark Seed-TTS-eval, rivaling the most powerful closed-source systems.
 
-| Model | Params | Open-source | EN WER (%) ↓ | EN SIM (%) ↑ | ZH CER (%) ↓ | ZH SIM (%) ↑ |
-|---|---:|:---:|---:|---:|---:|---:|
-| DiTAR | 0.6B | ❌ | 1.69 | 73.5 | 1.02 | 75.3 |
-| FishAudio-S1 | 4B | ❌ | 1.72 | 62.57 | 1.22 | 72.1 |
-| Seed-TTS |  | ❌ | 2.25 | 76.2 | 1.12 | 79.6 |
-| MiniMax-Speech |  | ❌ | 1.65 | 69.2 | 0.83 | 78.3 |
-|  |  |  |  |  |  |  |
-| CosyVoice | 0.3B | ✅ | 4.29 | 60.9 | 3.63 | 72.3 |
-| CosyVoice2 | 0.5B | ✅ | 3.09 | 65.9 | 1.38 | 75.7 |
-| CosyVoice3 | 0.5B | ✅ | 2.02 | 71.8 | 1.16 | 78 |
-| CosyVoice3 | 1.5B | ✅ | 2.22 | 72 | 1.12 | 78.1 |
-| F5-TTS | 0.3B | ✅ | 2 | 67 | 1.53 | 76 |
-| SparkTTS | 0.5B | ✅ | 3.14 | 57.3 | 1.54 | 66 |
-| FireRedTTS | 0.5B | ✅ | 3.82 | 46 | 1.51 | 63.5 |
-| FireRedTTS-2 | 1.5B | ✅ | 1.95 | 66.5 | 1.14 | 73.6 |
-| Qwen2.5-Omni | 7B | ✅ | 2.72 | 63.2 | 1.7 | 75.2 |
-| FishAudio-S1-mini | 0.5B | ✅ | 1.94 | 55 | 1.18 | 68.5 |
-| IndexTTS2 | 1.5B | ✅ | 2.23 | 70.6 | 1.03 | 76.5 |
-| VibeVoice | 1.5B | ✅ | 3.04 | 68.9 | 1.16 | 74.4 |
-| HiggsAudio-v2 | 3B | ✅ | 2.44 | 67.7 | 1.5 | 74 |
-| VoxCPM | 0.5B | ✅ | 1.85 | 72.9 | **0.93** | 77.2 |
-| Qwen3-TTS | 0.6B | ✅ | 1.68 | 70.39 | 1.23 | 76.4 |
-| Qwen3-TTS | 1.7B | ✅ | **1.5** | 71.45 | 1.33 | 76.72 |
-|  |  |  |  |  |  |  |
-| MossTTSDelay | 8B | ✅ | 1.79 | 71.46 | 1.32 | 77.05 |
-| MossTTSLocal | 1.7B | ✅ | 1.85 | **73.42** | 1.2 | **78.82** |
+| Model | EN WER (%) ↓ | EN SIM (%) ↑ | ZH CER (%) ↓ | ZH SIM (%) ↑ |
+|---|---:|---:|---:|---:|
+| MossTTSDelay (8B) | 1.79 | 71.46 | 1.32 | 77.05 |
+| MossTTSLocal (1.7B) | 1.85 | **73.42** | 1.2 | **78.82** |
+
+## Citation
+If you use this code or result in your research, please cite:
+```tex
+@misc{gong2026mossaudiotokenizerscalingaudiotokenizers,
+      title={MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models}, 
+      author={Yitian Gong and Kuangwei Chen and Zhaoye Fei and Xiaogui Yang and Ke Chen and Yang Wang and Kexin Huang and Mingshu Chen and Ruixiao Li and Qingyuan Cheng and Shimin Li and Xipeng Qiu},
+      year={2026},
+      eprint={2602.10934},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD},
+      url={https://arxiv.org/abs/2602.10934}, 
+}
+```