CASA-Qwen2_5-VL-3B
kyutai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 · 图像→ 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 ↗DISCOVER & COMPARE
探索 AI 模型 26
helium-1-2b
kyutai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 ↗helium-1-preview-2b
kyutaiHelium-1 preview is a lightweight language model with 2B parameters, targeting edge and mobile devices. It supports the following languages: English, French, German, Italian, Portuguese, Spanish. ⚠️ Helium-1 Preview is a base model, which was not fine-tuned to follow instructions or human preferences. For most downstream use cases, the model should be aligned with supervised fine-tuning, RLHF or related methods. The intended use of the Helium model is research and development of natural language processing systems, including but not limited to language generation and understanding. The model can be used in English, French, German, Italian, Portuguese and Spanish. For most downstream use cases, the model should be aligned with supervised fine-tuning, RLHF or related methods.
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 ↗hibiki-1b-pytorch-bf16
kyutai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 文本
价格待核验多模态与渠道费用须分别核对
查看详情 ↗hibiki-2b-pytorch-bf16
kyutai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 ↗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 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗mimi
kyutaiMimi codec is a state-of-the-art audio neural codec, developped by Kyutai, that combines semantic and acoustic information into audio tokens running at 12.5Hz and a bitrate of 1.1kbps. Mimi is a high-fidelity audio codec leveraging neural networks. It introduces a streaming encoder-decoder architecture with quantized latent space, trained in an end-to-end fashion. It was trained on speech data, which makes it particularly adapted to train speech language models or text-to-speech systems.
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 ↗moshika-candle-q8
kyutai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 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 ↗moshika-mlx-q4
kyutai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 ↗moshika-mlx-q8
kyutai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 ↗moshika-pytorch-bf16
kyutaiMoshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. Moshi also predicts time-aligned text tokens as a prefix to audio tokens. This “Inner Monologue” method significantly improves the linguistic quality of generated speech and provides streaming speech recognition and text-to-speech. As a result, Moshi is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice. The model can be used as a conversational agent for casual conversations, basic facts and advice (e.g. recipes, trivia), roleplay, etc. However, the model has limited abilities for complex tasks and cannot access tools, but rather focues on natural, low-latency interactions. Some components of the model can be used independently or repurposed relatively easily. For instance the Mimi codec is a state-of-the-art audio neural codec that combines semantic and acoustic information into audio tokens running at 12Hz and a bitrate of 1.1kbps, which make it particularly adapted to train speech language models or text-to-speech systems.. Regarding the main Moshi architecture, other downstream usecases would require some finetuning / domain adaptation.
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 ↗moshika-pytorch-q8
kyutai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 ↗moshika-rag-pytorch-bf16
kyutai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 音频→ 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 ↗moshiko-candle-q8
kyutaiMoshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. Moshi also predicts time-aligned text tokens as a prefix to audio tokens. This “Inner Monologue” method significantly improves the linguistic quality of generated speech and provides streaming speech recognition and text-to-speech. As a result, Moshi is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice. The model can be used as a conversational agent for casual conversations, basic facts and advice (e.g. recipes, trivia), roleplay, etc. However, the model has limited abilities for complex tasks and cannot access tools, but rather focues on natural, low-latency interactions. Some components of the model can be used independently or repurposed relatively easily. For instance the Mimi codec is a state-of-the-art audio neural codec that combines semantic and acoustic information into audio tokens running at 12Hz and a bitrate of 1.1kbps, which make it particularly adapted to train speech language models or text-to-speech systems.. Regarding the main Moshi architecture, other downstream usecases would require some finetuning / domain adaptation.
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 ↗moshiko-mlx-q4
kyutaiMoshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. Moshi also predicts time-aligned text tokens as a prefix to audio tokens. This “Inner Monologue” method significantly improves the linguistic quality of generated speech and provides streaming speech recognition and text-to-speech. As a result, Moshi is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice. The model can be used as a conversational agent for casual conversations, basic facts and advice (e.g. recipes, trivia), roleplay, etc. However, the model has limited abilities for complex tasks and cannot access tools, but rather focues on natural, low-latency interactions. Some components of the model can be used independently or repurposed relatively easily. For instance the Mimi codec is a state-of-the-art audio neural codec that combines semantic and acoustic information into audio tokens running at 12Hz and a bitrate of 1.1kbps, which make it particularly adapted to train speech language models or text-to-speech systems.. Regarding the main Moshi architecture, other downstream usecases would require some finetuning / domain adaptation.
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 ↗moshiko-mlx-q8
kyutai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 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 ↗moshiko-pytorch-bf16
kyutaiMoshi is a speech-text foundation model and full-duplex spoken dialogue framework Moshi is a speech-text foundation model that casts spoken dialogue as speech-to-speech generation. Starting from a text language model backbone, Moshi generates speech as tokens from the residual quantizer of a neural audio codec, while modeling separately its own speech and that of the user into parallel streams. This allows for the removal of explicit speaker turns, and the modeling of arbitrary conversational dynamics. Moshi also predicts time-aligned text tokens as a prefix to audio tokens. This “Inner Monologue” method significantly improves the linguistic quality of generated speech and provides streaming speech recognition and text-to-speech. As a result, Moshi is the first real-time full-duplex spoken large language model, with a theoretical latency of 160ms, 200ms in practice. - **Developed by:** Kyutai - **Model type:** Multimodal speech-text foundation model - **Language(s) (NLP):** English - **License:** CC-BY
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 ↗moshiko-pytorch-q8
kyutai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 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 ↗personaplex-rl-seamless
kyutai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 音频
价格待核验多模态与渠道费用须分别核对
查看详情 ↗pocket-tts
kyutai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 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 ↗Supports Python 3.10, 3.11, 3.12, 3.13 and 3.14. Requires PyTorch 2.5+. Does not require the gpu version of PyTorch. 🔊 Demo | 🐱💻GitHub Repository | 🤗 Hugging Face Model Card | ⚙️ Tech report | 📄 Paper | 📚 Documentation > [!NOTE] > **New (August 2026):** We've released the training code! Check out `training/` to start training your own models. > Open a PR to add your model to the Models trained by the community section.
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 ↗Sequential_Helium_6B
kyutai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 ↗stt-1b-en_fr-trfs
kyutai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 ↗stt-2.6b-en-trfs
kyutaiThis is a model for streaming speech-to-text (STT, also known as automatic speech recognition, ASR). Unlike offline speech-to-text, where the model needs the entire audio to produce the transcript, our model starts to output the transcript as soon as a few seconds of audio become available. The model architecture is a Transformer that consumes audio tokenized by Mimi (see the Moshi paper) and outputs text tokens. The frame rate is 12.5 Hz and each audio frame is represented by 32 audio tokens. We release two models: - `kyutai/stt-1b-en_fr`, an English and French model with ~1B parameters, a 0.5 second delay, and a semantic VAD. - `kyutai/stt-2.6b-en`, an English-only model with ~2.6B parameters and a 2.5 second delay.
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 ↗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。