全站搜索

AI 模型 22

• TTS-models↗

  hkilang

  本儲存庫包含香港圍頭話及客家話文字轉語音之 ONNX 模型。當選擇離線推導模式時，朗讀器程式會使用其進行模型推導，於程式內直接產生音訊。

• higgs-tts-3-4b↗

  bosonai

  Higgs TTS 3 is built for voice chat: it **speaks, not just reads**. It turns model responses into expressive conversational speech across **100+ languages**, with **zero-shot voice cloning** and **inline control** over emotion, style, prosody, pauses, and sound effects. > [!TIP] > Released for research and non-commercial use under the **Boson Higgs TTS 3 Research and Non-Commercial License**. Production, hosted APIs, embedding in a product/service, or reselling the model requires a separate commercial license. Prohibited: voice cloning without consent, impersonation, fraud, election deception, biometric surveillance, or any unlawful use. > [!TIP] > **Free for digital creators — including monetized content.** Under the license's **Creator Use Grant**, creators may use Higgs TTS 3 to make and monetize podcasts, videos, and social posts for free. The one requirement is to credit *Boson AI's Higgs Audio* — either in the audio or prominently in the accompanying text (e.g., the video description or show notes). Suggested credit: *"This audio was created with Boson AI's Higgs Audio — https://www.boson.ai/higgs-audio"*. See the Creator Use section below.

• MOSS-VoiceGenerator↗

  OpenMOSS-Team

  MOSS‑TTS Family is an open‑source **speech and sound generation model family** from MOSI.AI and the OpenMOSS team. 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. 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 Voice Generator** is an open-source voice generation system designed to enable the creation of custom speaker timbres from free-form textual descriptions. This model allows users to generate voices that reflect specific characters, personalities, and emotions. It is particularly notable for its ability to produce speech with natural-sounding emotional expressiveness, providing a realistic and nuanced listening experience. As an open-source tool, MOSS Voice Generator is suitable for a variety of applications, such as audiobooks, game dubbing, role-playing agents, and conversational assistants.

• MOSS-Audio-Tokenizer-v2↗

  OpenMOSS-Team

  This is the code for the 48khz stereo version of MOSS-Audio-Tokenizer presented in MOSS-Audio-Tokenizer: Scaling Audio Tokenizers for Future Audio Foundation Models. **MOSS-Audio-Tokenizer-v2** is a unified discrete audio tokenizer based on the **Cat** (**C**ausal **A**udio **T**okenizer with **T**ransformer) architecture. Scaling to 2 billion parameters, it functions as a unified discrete interface, delivering both lossless-quality reconstruction and high-level semantic alignment. * **Extreme Compression & Variable Bitrate**: It compresses 48kHz stereo audio into a remarkably low frame rate of 12.5Hz. Utilizing a 32-layer Residual Vector Quantization stack, it supports high-fidelity reconstruction across a wide range of bitrates. * **Pure Transformer Architecture**: The model features a "CNN-free" homogeneous architecture built entirely from Causal Transformer blocks. With 2B combined parameters (Encoder + Decoder), it ensures exceptional scalability and supports low-latency streaming inference. * **Large-Scale General Audio Training**: Trained on 3 million hours of diverse audio data, the model excels at encoding and reconstructing all audio domains, including speech, sound effects, and music. * **Unified Semantic-Acoustic Representation**: While achieving state-of-the-art reconstruction quality, Cat produces discrete tokens that are "semantic-rich," making them ideal for downstream tasks like speech understanding (ASR) and generation (TTS). * **Fully Trained From Scratch**: Cat does not rely on any pretrained encoders (such as HuBERT or Whisper) or distillation from teacher models. All representations are learned autonomously from raw data. * **End-to-End Joint Optimization**: All components—including the encoder, quantizer, decoder, discriminator, and a decoder-only LLM for semantic alignment—are optimized jointly in a single unified training pipeline.

• Supertonic-3-CoreML↗

  aufklarer

  **First-party CoreML export** of Supertonic-3's four non-autoregressive flow-matching graphs, for on-device iOS / Apple Neural Engine. Built by our own pipeline (`speech-models/stmodels`): weights lifted from the `Supertone/supertonic-3` ONNX initializers → PyTorch `nn.Module` → `coremltools` (`mlprogram`, FP32, iOS18+). Text/duration use **fixed T=128** (relpos attention has T-dependent pad widths — pad/segment text to 128); vocoder + vector-estimator use a dynamic latent-length `RangeDim`. The host runs the flow-matching ODE loop (`vector_estimator` ×`total_steps`) — the graphs contain no control flow. Assets to drive them: `tts.json`, `unicode_indexer.json` (G2P-free tokenizer table), `voice_styles/*.json`. > FP32 = parity reference. For **ANE residency**, use the mixed-precision > `Supertonic-3-CoreML-FP16` — vocoder + duration FP16, > text-encoder + vector-estimator FP32; measured transparent at **47–51 dB** mag-STFT SNR.

• magpie_tts_multilingual_357m↗

  NVIDIA

  > [!Note] > July 21, 2026: MagpieTTS v2607 was released with support for 3 new languages (Arabic, Korean, Portuguese). > > For the older checkpoints, refer to below tags: > > - Released on March 2026, v2602. > - Released on January 2026, v2512. MagpieTTS is an end-to-end multilingual neural text-to-speech model that synthesizes speech using 5 English speaker voices — Aria, Jason, Leo, Sofia, and John Van Stan — across 12 languages: Arabic (ar), Chinese (zh), English (en), French (fr), German (de), Hindi (hi), Italian (it), Japanese (ja), Korean (ko), Portuguese (pt), Spanish (es), and Vietnamese (vi). The model adopts a transformer encoder–decoder architecture that autoregressively predicts discrete audio codec tokens, using multi-codebook prediction (typically 8 codebooks) with frame stacking (factor = 2) and a local transformer for fine-grained refinement of high-fidelity audio. To improve robustness and controllability, training incorporates attention priors for stable text-to-audio alignment, classifier-free guidance (CFG) for stronger conditioning, and Group Relative Policy Optimization (GRPO) for preference-aligned generation. At inference time, MagpieTTS supports batched synthesis of complete utterances as well as long-form generation of extended text via a sliding-window mechanism; the predicted codec tokens are then decoded into speech waveforms by a frozen pretrained audio codec model (NanoCodec). This release also removed zero-shot voice-cloning capability for security reasons, and added IPA grapheme-to-phoneme (G2P) support for custom dictionaries and code-switching, and updated G2P support for English-to-Katakana code-switching. MagpieTTS is for developers, researchers, and product teams building multilingual speech applications that need consistent speaker voices across 12 languages. Typical applications include cascade voice agents, audiobook and content narration, accessibility tools, dubbing and localization pipelines, and interactive media. IPA grapheme-to-phoneme (G2P) support for custom dictionaries and code-switching (including English-to-Katakana) also enables mixed-language content and domain-specific pronunciation.

• F5-Spanish↗

  jpgallegoar

  The F5-TTS model is finetuned specifically for Spanish language speech synthesis. This project aims to deliver high-quality, regionally diverse speech synthesis capabilities for Spanish speakers. This model is released under the CC0-1.0 license, which allows for free usage, modification, and distribution. - Voxpopuli Dataset, with mainly Peninsular Spain accents - Crowdsourced high-quality Spanish speech data: - Argentinian Spanish - Chilean Spanish - Colombian Spanish - Peruvian Spanish - Puerto Rican Spanish - Venezuelan Spanish - TEDx Spanish Corpus

• Ming-3.0-tts-0.5B↗

  inclusionAI

  Ming-3.0-tts-0.5B Dense 0.5B multilingual speech synthesis with paralinguistic and free-form control. This repository contains **Ming-3.0-tts-0.5B**, the dense Ming-3.0-tts checkpoint built on Qwen2.5-0.5B. The checkpoint includes the backbone, DiT head, audio tokenizer, speaker encoder and text tokenizer. > **Inference requires the Ming-3.0-tts GitHub repository.** This Hugging Face repository is for checkpoint distribution and does not provide a standalone inference setup. Clone the GitHub repository and follow its README for the current dependencies, inference code and usage instructions. The CLI scripts and Python APIs referenced below are provided by the GitHub repository.

• tts_ru_free_hf_vits_low_multispeaker↗

  utrobinmv

• VieNeu-TTS-v3-Turbo-GGUF↗

  phuocnguyen90

  This repository contains the official GGUF quantized model package for **VieNeu-TTS v3 Turbo (48 kHz)**, fully integrated and supported natively in **audio.cpp** (merged in PR #80). > **Model Credits & Acknowledgments**: This is a GGUF quantization of the original VieNeu-TTS-v3-Turbo model created by **pnnbao-ump**. All credit for the underlying architecture and model training goes to the original authors. It packs both the compressed Qwen3 talker backbone and the speech tokenizer/decoder weights into a single optimized **163 MB** file, enabling instant load times and ultra-fast, torch-free C++ generation on CPU.