vermeer-XL-CA
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗DISCOVER & COMPARE
探索 AI 模型 85003
VibeVoice-1.5B
MicrosoftVibeVoice is a novel framework designed for generating expressive, long-form, multi-speaker conversational audio, such as podcasts, from text. It addresses significant challenges in traditional Text-to-Speech (TTS) systems, particularly in scalability, speaker consistency, and natural turn-taking. A core innovation of VibeVoice is its use of continuous speech tokenizers (Acoustic and Semantic) operating at an ultra-low frame rate of 7.5 Hz. These tokenizers efficiently preserve audio fidelity while significantly boosting computational efficiency for processing long sequences. VibeVoice employs a next-token diffusion framework, leveraging a Large Language Model (LLM) to understand textual context and dialogue flow, and a diffusion head to generate high-fidelity acoustic details. The model can synthesize speech up to **90 minutes** long with up to **4 distinct speakers**, surpassing the typical 1-2 speaker limits of many prior models.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-AcousticTokenizer
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-ASR
Microsoft**VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)**, with support for **Customized Hotwords** and over **50 languages**. ➡️ **Code:** microsoft/VibeVoice ➡️ **Demo:** VibeVoice-ASR-Demo ➡️ **Report:** VibeVoice-ASR Technical Report ➡️ **Finetuning:** Finetuning ➡️ **vLLM:** vLLM-VibeVoice-ASR - **🕒 60-minute Single-Pass Processing**: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to **60 minutes** of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-ASR-BitNet
Microsoft**VibeVoice-ASR-BitNet** is a compressed variant of VibeVoice-ASR optimized for **real-time inference on edge CPUs** — no GPU required. Through heterogeneous quantization, the model is compressed from 4.62 GB to **1.58 GB** while achieving **1.6–2.3× faster** inference than Whisper.cpp with real-time capability (RTF ➡️ **Report:** VibeVoice-ASR-BitNet Technical Report ➡️ **Base Model:** microsoft/VibeVoice-ASR This project was conducted by members of Microsoft Research. If you have suggestions, questions, or observe unexpected behavior, please contact us at VibeVoice@microsoft.com.
译文排队中 · 当前显示来源原文
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-ASR-HF
Microsoft**VibeVoice-ASR** is a unified speech-to-text model designed to handle **60-minute long-form audio** in a single pass, generating structured transcriptions containing **Who (Speaker), When (Timestamps), and What (Content)**, with support for **Customized Hotwords** and over **50 languages**. ➡️ **Demo:** VibeVoice-ASR-Demo ➡️ **Report:** VibeVoice-ASR Technical Report - **🕒 60-minute Single-Pass Processing**: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to **60 minutes** of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour.
译文排队中 · 当前显示来源原文
输入 音频 · 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-ASR-Streaming-1.5B
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-ASR-Streaming-7B
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
输入 音频→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VibeVoice-Realtime-0.5B
MicrosoftVibeVoice-Realtime is a **lightweight real‑time** text-to-speech model supporting **streaming text input** and **robust long-form speech generation**. It can be used to build realtime TTS services, narrate live data streams, and let different LLMs start speaking from their very first tokens (plug in your preferred model) long before a full answer is generated. It produces initial audible speech in **~300 ms** (hardware dependent). Although the model is primarily built for English, we found that it still exhibits a certain level of multilingual capability—and even performs reasonably well in some languages. We provide nine additional languages (German, French, Italian, Japanese, Korean, Dutch, Polish, Portuguese, and Spanish) for users to explore and share feedback. The model uses an interleaved, windowed design: it incrementally encodes incoming text chunks while, in parallel, continuing diffusion-based acoustic latent generation from prior context. Unlike the full multi-speaker long-form variants, this streaming model removes the semantic tokenizer and relies solely on an efficient acoustic tokenizer operating at an ultra-low frame rate (7.5 Hz).
译文排队中 · 当前显示来源原文
输入 文本→ 输出 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VidTok
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vidtwin
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗villa-x
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗VITRA-VLA-3B
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗vq-diffusion-ithq
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavecoder-ds-6.7b
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavecoder-pro-6.7b
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavecoder-ultra-6.7b
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base
MicrosoftThe base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. The model was pre-trained on 960h of Librispeech.
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base-plus
MicrosoftThe base model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli
译文排队中 · 当前显示来源原文
输入 文本→ 输出 向量
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base-plus-sd
MicrosoftThe model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base-plus-sv
MicrosoftThe model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base-sd
Microsoft基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。
基础资料已收录 · 缺失资料后续补充
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-base-sv
MicrosoftThe model was pretrained on 16kHz sampled speech audio with utterance and speaker contrastive loss. When using the model, make sure that your speech input is also sampled at 16kHz. The model was pre-trained on 960h of Librispeech. Authors: Sanyuan Chen, Chengyi Wang, Zhengyang Chen, Yu Wu, Shujie Liu, Zhuo Chen, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiong Xiao, Jian Wu, Long Zhou, Shuo Ren, Yanmin Qian, Yao Qian, Jian Wu, Michael Zeng, Furu Wei
译文排队中 · 当前显示来源原文
输入 待核验→ 输出 待核验
价格待核验多模态与渠道费用须分别核对
查看详情 ↗wavlm-large
MicrosoftThe large model pretrained on 16kHz sampled speech audio. When using the model, make sure that your speech input is also sampled at 16kHz. **Note**: This model does not have a tokenizer as it was pretrained on audio alone. In order to use this model **speech recognition**, a tokenizer should be created and the model should be fine-tuned on labeled text data. Check out this blog for more in-detail explanation of how to fine-tune the model. - 60,000 hours of Libri-Light - 10,000 hours of GigaSpeech - 24,000 hours of VoxPopuli
译文排队中 · 当前显示来源原文
输入 文本→ 输出 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗暂未找到匹配模型
可以调整厂商、分类或输入输出条件；新模型正持续收录。
COST EXPLORER
好模型，也要算好成本。
调整月度 Token 用量，直观比较不同模型的预估 API 开支。
1 M = 100 万 Token · 美元计价
仅比较同一渠道的基础文本 Token 报价
仅比较同一渠道的基础文本 Token 报价
使用已采集且单位可比的 USD / 百万 Token 渠道报价。报价为采集时快照；不计缓存优惠、阶梯价、推理额外输出与税费，请以来源的当前报价为准。
MODEL HANDBOOK
读懂模型，再做选择
API 价格应该怎么比较？+
先区分输入、输出和缓存价格，再使用同一任务和用量估算总费用。图像、音频和视频可能按张、时长或分辨率计费，不能直接与 Token 单价比较。
开放权重，就代表可以免费商用吗？+
不一定。必须逐一核对具体模型版本的许可证、商用限制及使用政策。自己部署还需要考虑显存、推理资源和运维费用。
排行榜第一，就是最适合我的模型吗？+
榜单取决于测试任务、版本与评测方法。建议用实际业务样本比较准确性、时延、稳定性和成本，再选择模型。