阴道3
思考
目录
Voxtral 3 推出是一个为实时设计的尖端语音agent SDK和最先进语音模型，跨50+语言的多步对话。 它结合了准确的抄录，自然语音合成和情感适应性，以及深层工具集成，实现无缝工作流程自动化。 通过Mistral的欧盟托管的API或自我部署提供，它既能保证数据主权，又能提供低纬度、接触中心的人性互动、虚拟助手和无手copilots。
语音转录和语音生成取得了很大进展，但构建端对端语音agents能够听，理性，互动，处理复杂工作流程仍然困难。
一个可靠的声音agent需要非常出色地做四件事(同时):
- 准确聆听各种语言、口音、扬声器和中断
- 关于用户在特定情况下的含义的深刻理由
- 用情感和表情自然说话
- 通过连接的系统在多个步骤上采取行动。
使所有四个国家能够可靠地实时合作仍然是一个挑战。
为了解决这个问题，我们引入了Voxtral 3：一个由最先进语音转文本和文本转语音模型组成的新家族，同时推出一个语音agent SDK，带来监听，思考，工具调用，并用一个单一的实时流线管道说话。
Voxtral 3是用来创建自然对话体验的，从接触中心agents和服务台到虚拟助手和无手copilots. 在支持数十种语言，表达式语音，复杂的推理，以及与你自己的工具和数据的深度融合下，用Voxtral构建的agents可以解释细微的意向，通过复杂的请求解释理性，并跨连接系统执行多步动作。
和其他Mistral型号一样，Voxtral 3家族也是为主权部署而设计的。 今天通过Mistral的欧盟托管的API或自行部署在您自己的基础设施上，它让各组织能够控制音频的处理地点，如何处理数据，以及是否保留对话。
要点
- 准确记录50多种语言的文字。 语音转文本模型Voxtral Small Translats 3是多语种转录中的最先进，识别谁的称是什么(diarization)，使用键词来提高它的精度(context-biasing). 它探测到有人说完话后，agents就可以毫不延迟地响应(回合末检测).
- 适应谈话的自然演说文本转语音模式 Voxtral mini TTS 3，推出新声调调整其情感，速度，以及基于对话背景的强调，支持35+语言和50+方言。
- 人类般的智慧在你(说话)指挥。 新的语音agent SDK结合了听，推理，工具调用，和说话的实时体验。 Agents可以检索信息，与商业系统互动，在通过电话或网络进行直播时完成任务。
- 支持声音明显准确的声音适应。 Voxtral的Pro Voice的改编可以复制演讲者独特的性格、情感范围、语言风格
- 你的声音AI，你的基础设施。 使用 Mistral 的欧盟托管的 API，或在自己的基础设施上部署 Voxtral 3. 在您的环境中保持敏感对话，并控制是否保留任何音频。
它听到50+语言，具有最先进精度。
Voxtral Transits 3代表着跨转录、对等化(何时发言)和背景偏差能力的重要里程碑。 得到支持的语文清单已扩大到50种，包括24种欧盟正式语文和许多低资源亚洲和印度语。
Small版本实现了最先进结果，跨越了对称化和多语种转录，包括英语，法语和西班牙语。 它的性能超过了Whisper,Scribe v2和Gemini 3.5 Transis. 迷你变体为4B参数，可以快速和准确的转录，价格为0.0035/min.
这两个模型都支持上下文偏差，其中关键术语和自由格式文本可以用于偏差抄录，并在技术方面改进召回。 这使得它们能够在具有特定域词汇的制作环境中使用，而不需要微调。
Voxtral Realtime Transit 3是一种实时的抄写模型，为代理使用案所建。 它在超过35种语言的亚500ms latency上实现了高质量的转录，包括有线化和上下文偏差。
转折后预测得到本土支持，既包含声学信息，也包含语义信息，以准确预测用户完成演讲的时间。 这允许低纬度语音agent应用程序，同时在用户过早中断时将假截断率降到最低。
用你或你客户的品牌自己的声音和当地方言
Voxtral Mini TTS 3.0，分批和实时提供，实现最先进表达和训导后35+语言和50+方言。 按每1M字符13美元计算，Voxtral Speech 3比OpenAI TTS-1,Deepgram,ElevenLabs Flash和Gemini Flash的可比模型运行成本要低。
语音模型含蓄地诠释了上下文的语义意义，产生了跨越各种情感和语言的自然语音。 新的和改进的功能包括：从30+分钟的抽样音频中进行语音克隆，根据(IF)进行自定义的即时指示，背景TTS，以及一个词汇库，所有这些都服务于部署中语音可靠性的目标。 明确IF的变量包括情感、速度和强调。
提示
所有自然声音的演说都依赖于情感，这决定了它的音节，节奏，节奏，强调，以及过渡。 Voxtral TTS在本地解释一个提示的文本上下文，以确定情感和语音风格，使模型在自然语音上本质上更好，而不需要额外的指令或语音提示。
以表现力，数字和独特名称来说明Voxtral山峰攀登。
提示
语音用35种语言和50多种方言发声。
Voxtral TTS支持超过35种语言和区域方言。 我们的多语种evals坚持方言在发音，正式与非正式的注册，拼写，动词，以及地方惯例(时间，日期，温度，地址，货币)上的差异。
Voxtral 3 多语种图书馆
语音预设有18种语言：阿拉伯语(Emirati，现代标准)，巴西语(葡萄牙语)，加泰罗尼亚语，中文(曼达林语)，荷兰语，英语(美国，英国)，法语(法国)，德语，希腊语，印地语，意大利语，韩语，挪威语，俄语，西班牙语(西班牙)，越南语。
语音agent控制了整个对话。
Voxtral 3 推出 a voice agent SDK，建于LiveKit上，作为一条流线管道运行语音，推理，语音输出。 Voxtral Mini Trancis Realtime 3在呼叫者发言完毕时会聆听和侦测，一个一般的模型——如Mistral Small——理性和调用工具，以及Voxtral Speech 3在至今为止的谈话基调中回复。 没有舞台等待它之前的一个，所以每个转弯在一秒内完成，agent在呼叫者削减进入时停止说话。
在电话通话期间，agent可以使用功能呼叫，网络搜索，以及检索到自己的系统，验证呼叫者的身份，检查账单，或者预订预约。 它在SIP上响应和定位调用，在WebRTC上运行浏览器和应用程序，并连接到你已经使用的电话，IVR和联系中心软件。
每个舞台都是单独的模型，因此可以在不重写agent的情况下更改LLM，语音，或语言，并运行Mistral在欧洲的API或你自己的基础设施上的全部堆栈。
开始吧
Voxtral 3今天通过Mistral API提供，通过我们的欧洲，美国和全球端点托管。
您可以在 Studio 游戏场测试语音 agents，音频转录，语音生成，语音克隆。
要运行完整的堆叠或在一个私人云，与我们的团队。
缩略语 3
新设
最高精度语音转录模型。 最先进多语种转录和对位化，支持超过50种语言和背景偏差。
译名
音频
$0.004
分钟
Voxtral 小型转录机 3
新设
高效，低纬度的语音转录模型。 支持用50多种语言进行多语种的转录、拓扑和背景偏差。
译名
音频( 批次)
$0.0035
分钟
Voxtral 迷你转写实时 3
为代理用案打造的实时抄录模式，在40+语言的下500ms空闲时提供高质量的抄录。
译名
音频
$0.008
分钟
Voxtral 发言 3
最先进语言和50+方言的表达和教学
语音
投入
$13
1M 字符数
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
Voxtral 3
Thinking
Summary
Voxtral 3 introduces a cutting-edge voice agent SDK and state-of-the-art speech models designed for real-time, multi-step conversations across 50+ languages. It combines accurate transcription, natural speech synthesis with emotional adaptability, and deep tool integration for seamless workflow automation. Available via Mistral’s EU-hosted API or self-deployment, it ensures data sovereignty while delivering low-latency, human-like interactions for contact centers, virtual assistants, and hands-free copilots.
Speech transcription and voice generation have come a long way, but building end-to-end voice agents that can listen, reason, interact, and handle complex workflows remains difficult.
A reliable voice agent needs to do four things very well (and simultaneously):
- Listen accurately across languages, accents, speakers, and interruptions,
- Reason deeply about what users mean in specific contexts,
- Speak naturally with emotion and expression, and
- Take action over multiple steps through connected systems.
Getting all four to work together reliably in real time remains a challenge.
To address this, we introduce Voxtral 3: a new family of state-of-the-art speech-to-text and text-to-speech models, alongside a voice agent SDK that brings listening, thinking, tool calling, and speaking into a single real-time streaming pipeline.
Voxtral 3 is built to create natural conversational experiences, from contact-center agents and service desks to virtual assistants and hands-free copilots. With support for dozens of languages, expressive speech, complex reasoning, and deep integration with your own tools and data, agents built with Voxtral can interpret nuanced intent, reason through sophisticated requests, and execute multi-step actions across connected systems.
As with other Mistral models, the Voxtral 3 family is designed for sovereign deployment. Available today through Mistral's EU-hosted API or for self-deployment on your own infrastructure, it gives organizations control over where audio is processed, how data is handled, and whether conversations are retained.
Highlights
- Accurate transcription across 50+ languages. The speech-to-text model, Voxtral Small Transcribe 3, is state-of-the-art in multilingual transcription, identifying who said what (diarization), using keyphrases to improve its accuracy (context-biasing). It detects when someone has finished speaking so agents can respond without delay (end-of-turn detection).
- Natural speech that adapts to the conversation. The text-to-speech model, Voxtral Mini TTS 3, introduces new voices that adjust their emotion, pace, and emphasis based on conversational context, with support for 35+ languages and 50+ dialects.
- Human-like intelligence at your (spoken) command. The new voice agent SDK combines listening, reasoning, tool calling, and speaking into a real-time experience. Agents can retrieve information, interact with business systems, and complete tasks during live conversations over phone or web.
- Pro Voice for distinctly accurate voice adaptation. For professional use cases where basic voice cloning does not suffice, Voxtral’s Pro Voice adaptation is able to reproduce a speaker’s distinctive character, emotional range, and speaking style across languages, using just 30 minutes of audio.
- Your voice AI, on your infrastructure. Use Mistral's EU-hosted API or deploy Voxtral 3 on your own infrastructure. Keep sensitive conversations within your environment and control whether any audio is retained.
It hears 50+ languages, with state-of-the-art accuracy.
Voxtral Transcribe 3 represents a significant milestone across transcription, diarization (who spoke when) and context biasing capabilities. The supported list of languages is expanded to 50, including 24 official EU languages and many low-resource Asian and Indic languages.
The Small version achieves state-of-the-art results across diarization and multilingual transcription, including in English, French and Spanish. It outperforms Whisper, Scribe v2 and Gemini 3.5 Transcribe. The Mini variant is 4B parameters, enabling fast and accurate transcriptions at a price of $0.0035/min.
Both models support context biasing, where key terms and free-form text can be given to bias the transcription and improve recall on technical terms. This enables them to be used in production settings with domain-specific vocabulary without the need for fine-tuning.
Voxtral Realtime Transcribe 3 is a realtime transcription model built for agentic use-cases. It achieves high-quality transcriptions at sub-500ms latency in over 35 languages, including with diarization and context biasing.
End-of-turn prediction is natively supported, incorporating both acoustic and semantic information to accurately predict when a user is finished speaking. This allows for low-latency voice agent applications, while minimizing false cut-off rates when the user is prematurely interrupted.
It answers with the right emotion, in your or your customer’s brand's own voice and local dialect.
Voxtral Mini TTS 3.0, available in batch and realtime, achieves state-of-the-art expressiveness and instruction following for 35+ languages and 50+ dialects. At $13 per 1M characters, Voxtral Speech 3 costs less to run than comparable models from OpenAI TTS-1, Deepgram, ElevenLabs Flash and Gemini Flash.
The speech model implicitly interprets the semantic meaning of context better, producing natural speech across a diverse range of emotions and languages. New and improved features include voice cloning from 30+ minutes of sampled audio, custom prompt instruction following (IF), contextual TTS, and a vocabulary library, all of which serve the goal of speech reliability in deployment. Variables for Explicit IF include emotion, pacing, and emphasis.
Prompt
All natural-sounding speech relies on emotion, which determines its prosody, rhythm, pacing, emphasis, and transitions. Voxtral TTS natively interprets a prompt’s text context to determine the emotion and voice style, making the model inherently better at natural speech without requiring additional instructions or voice prompts.
Illustrating Voxtral hill-climbing in expressiveness, numbers and unique names.
Prompt
Speech sounds local in 35 languages and over 50 dialects.
Voxtral TTS supports over 35 languages and regional dialects. Our multilingual evals adhere to dialect differences in pronunciation, formal vs. informal register, spelling, verbosity, and locale conventions (time, dates, temperatures, addresses, currencies).
Voxtral 3 multilingual library
Voice Presets are available in 18 languages: Arabic (Emirati, Modern Standard), Brazilian (Portuguese), Catalan, Chinese (Mandarin), Dutch, English (American, British), French (France), German, Greek, Hindi, Italian, Korean, Norwegian, Russian, Spanish (Spain), and Vietnamese.
The voice agent is in control of the whole conversation.
Voxtral 3 introduces a voice agent SDK, built on LiveKit, that runs speech in, reasoning, and speech out as one streaming pipeline. Voxtral Mini Transcribe Realtime 3 listens and detects when the caller has finished speaking, a general model—like Mistral Small—reasons and calls tools, and Voxtral Speech 3 replies in the tone of the conversation so far. No stage waits for the one before it, so each turn completes in under one second, and the agent stops talking when the caller cuts in.
During a call, the agent can verify a caller's identity, check a bill, or book an appointment, using function calling, web search, and retrieval over your own systems. It answers and places calls over SIP, runs in browsers and apps over WebRTC, and connects to the telephony, IVR, and contact-center software you already use.
Each stage is a separate model, so you can change the LLM, the voice, or the language without rewriting the agent, and run the whole stack on Mistral's API in Europe or on your own infrastructure.
Get started.
Voxtral 3 is available today through the Mistral API, hosted through our European, US, and global endpoints.
You can test out voice agents, audio transcription, speech generation, and voice cloning in the Studio playgrounds.
To run the full stack on-premises or in a private cloud, talk to our team.
Voxtral Small Transcribe 3
New
Highest accuracy speech transcription model. State-of-the-art multilingual transcription and diarization, with support for over 50 languages and context biasing.
Transcription
Audio
$0.004
/min
Voxtral Mini Transcribe 3
New
Efficient, low-latency speech transcription model. Supports multilingual transcription, diarization and context biasing in over 50 languages.
Transcription
Audio (Batch)
$0.0035
/min
Voxtral Mini Transcribe Realtime 3
A realtime transcription model built for agentic use-cases, delivering high-quality transcriptions at sub-500ms latency across 40+ languages.
Transcription
Audio
$0.008
/min
Voxtral Speech 3
State-of-the-art expressiveness and instruction following across 35+ languages and 50+ dialects
Voice
Input
$13
/1M chars
Auto-fetched and translated by AI Atlas. All rights belong to the original author.