--- title: "TypeSafe | Micdrop" description: "Classify each turn of the user with TypeSafe Jev: typed questions (choice, score, yes or no) answered with calibrated probabilities in a few hundred ms, to route the answer before the LLM." url: "https://micdrop.dev/docs/ai-integration/provided-integrations/typesafe" --- * [Getting Started](/docs/getting-started) * [Examples and demos](/docs/examples) * [Client (Browser)](/docs/client) * [Installation](/docs/client/installation) * [React Hooks](/docs/client/react-hooks) * [Start/Stop Call](/docs/client/start-stop-call) * [Pause/Resume Call](/docs/client/pause-resume-call) * [Mute/Unmute Call](/docs/client/mute-unmute-call) * [Call State](/docs/client/call-state) * [Display Conversation Messages](/docs/client/display-conversation-messages) * [Handling Tool Calls](/docs/client/handling-tool-calls) * [Device Management](/docs/client/devices-management) * [Voice Activity Detection (VAD)](/docs/client/vad) * [Turn Detection](/docs/client/turn-detection) * [Reducing Latency](/docs/client/latency) * [Error Handling](/docs/client/error-handling) * Utility Classes * [Mic](/docs/client/utility-classes/mic) * [MicdropClient](/docs/client/utility-classes/micdrop-client) * [MicRecorder](/docs/client/utility-classes/mic-recorder) * [Speaker](/docs/client/utility-classes/speaker) * [Client (React Native)](/docs/react-native) * [Installation](/docs/react-native/installation) * [Hooks and Call State](/docs/react-native/hooks) * [Audio Output and Devices](/docs/react-native/audio-output) * [Voice Activity Detection (VAD)](/docs/react-native/vad) * [Turn Detection](/docs/react-native/turn-detection) * [Using Another Audio Library](/docs/react-native/custom-audio) * [Server (Node.js)](/docs/server) * [Installation](/docs/server/installation) * [With Fastify](/docs/server/with-fastify) * [With NestJS](/docs/server/with-nestjs) * [Auth and Parameters](/docs/server/auth-and-parameters) * [First Message](/docs/server/first-message) * [Dictation and Text-Only Calls](/docs/server/dictation) * [Realtime Models](/docs/server/realtime) * [Partial Messages](/docs/server/partial-messages) * [Save Messages](/docs/server/save-messages) * [Resume a Conversation](/docs/server/resume-conversation) * [Recording Audio](/docs/server/recording-audio) * [Error Handling](/docs/server/error-handling) * [Tools](/docs/server/tools) * [Extract Value from Answer](/docs/server/extract) * [Classifier](/docs/server/classifier) * [Auto End Call](/docs/server/auto-end-call) * [Semantic Turn Detection](/docs/server/semantic-turn-detection) * [Noise Filtering](/docs/server/noise-filtering) * [Micdrop Protocol](/docs/server/protocol) * [AI Integrations](/docs/ai-integration) * Provided Integrations * [AI SDK](/docs/ai-integration/provided-integrations/ai-sdk) * [Cartesia](/docs/ai-integration/provided-integrations/cartesia) * [ElevenLabs](/docs/ai-integration/provided-integrations/elevenlabs) * [Gemini](/docs/ai-integration/provided-integrations/gemini) * [Gladia](/docs/ai-integration/provided-integrations/gladia) * [Gradium](/docs/ai-integration/provided-integrations/gradium) * [Kokoro](/docs/ai-integration/provided-integrations/kokoro) * [Mistral](/docs/ai-integration/provided-integrations/mistral) * [OpenAI](/docs/ai-integration/provided-integrations/openai) * [Piper](/docs/ai-integration/provided-integrations/piper) * [Pocket TTS](/docs/ai-integration/provided-integrations/pocket-tts) * [Qwen3-TTS](/docs/ai-integration/provided-integrations/qwen-tts) * [TypeSafe](/docs/ai-integration/provided-integrations/typesafe) * [Whisper](/docs/ai-integration/provided-integrations/whisper) * Custom Integrations * [Agent (LLM)](/docs/ai-integration/custom-integrations/custom-agent) * [Speech-to-Text (STT)](/docs/ai-integration/custom-integrations/custom-stt) * [Text-to-Speech (TTS)](/docs/ai-integration/custom-integrations/custom-tts) * [Classifier](/docs/ai-integration/custom-integrations/custom-classifier) * Fallback Strategies * [FallbackAgent](/docs/ai-integration/fallback-strategies/agent-fallback) * [FallbackSTT](/docs/ai-integration/fallback-strategies/stt-fallback) * [FallbackTTS](/docs/ai-integration/fallback-strategies/tts-fallback) * [Local Models](/docs/ai-integration/local-models) * [Local LLM](/docs/ai-integration/local-models/agent) * [Local STT](/docs/ai-integration/local-models/speech-to-text) * [Local TTS](/docs/ai-integration/local-models/text-to-speech) * [Latency and Memory](/docs/ai-integration/local-models/performance) * [Explorations](/docs/ai-integration/local-models/explorations) * [MiniCPM5-2B](/docs/ai-integration/local-models/explorations/minicpm) * [Mistral 7B](/docs/ai-integration/local-models/explorations/mistral-7b) * [Voxtral Mini 3B](/docs/ai-integration/local-models/explorations/voxtral-stt) * [Voxtral TTS 4B](/docs/ai-integration/local-models/explorations/voxtral-tts) * [AuK and AuK-Flash](/docs/ai-integration/local-models/explorations/auk) * [IA Vocale Souveraine 🇫🇷🇪🇺](/docs/ai-integration/sovereign-voice-ai) * [Migration](/docs/migration) * [Upgrade to v3](/docs/migration/v3) [Micdrop](/) › [Documentation](/docs/getting-started) › [AI Integrations](/docs/ai-integration) › Provided Integrations # TypeSafe TypeSafe implementation of the [classifier](/docs/server/classifier) for [@micdrop/server](/docs/server). It runs [Jev](https://docs.typesafe.ai), a “System One” model from TypeSafe AI. Where an LLM writes an answer token by token, Jev answers a set of typed questions at once: pick a label, give a score, say yes or no. Each answer comes with calibrated probabilities, in a few hundred ms, which is fast enough to route the answer before the LLM starts. ## Installation Terminal window ``` npm install @micdrop/typesafe ``` ## Usage with MicdropServer ``` import { MicdropServer } from '@micdrop/server'import { choice, noul, score, TypesafeClassifier } from '@micdrop/typesafe' const classifier = new TypesafeClassifier({ apiKey: process.env.TYPESAFE_API_KEY || '', questions: { intent: choice( 'What does the user in `turn` want? Read `history` for context.', { billing: 'A charge, an invoice, a refund', outage: 'The service is down or slow', cancel: 'Cancel the subscription or switch provider', other: null, } ), frustration: score('How frustrated is the user in `turn`?', [ 'Calm', 'Annoyed', 'Angry', ]), wantsHuman: noul('Does the user in `turn` ask for a human?'), },}) new MicdropServer(socket, { stt, agent, tts, classifier, classifierOptions: { // The client receives each classification sendToClient: true, // The answer waits for the classification of its turn, up to 1 s waitBeforeAnswer: true, },}) ``` The server classifies each turn of the user when it ends. It works with any speech to text, and with [realtime models](/docs/server/realtime). See [Classifier](/docs/server/classifier) for the server options, routing the answer in `onBeforeAnswer`, and reading the results in the client. ## Usage without MicdropServer `classify()` takes a text or any JSON, and resolves with the classification: ``` import { noul, TypesafeClassifier } from '@micdrop/typesafe' const classifier = new TypesafeClassifier({ apiKey: process.env.TYPESAFE_API_KEY || '', questions: { urgent: noul('Does the user in `turn` sound urgent?') },}) const classification = await classifier.classify({ history: [], turn: 'My internet has been down since yesterday!',})console.log(classification?.result.answers.urgent.noul) ``` A plain text works too, with questions that read it as a whole: ``` const classifier = new TypesafeClassifier({ questions: { urgent: noul('Does this message sound urgent?') },}) await classifier.classify('My internet is down!') ``` ## State Jev reads a JSON state and answers the questions about it. The input is sent as the state as is, so in a call Jev reads the `MicdropTurnInput` of the server: ``` { "history": [ { "role": "user", "text": "My internet is down again." }, { "role": "assistant", "text": "Sorry to hear that. Since when?" } ], "turn": "Since this morning. And this is the third time this month."} ``` Questions point at these fields by name, between backticks: “Does the user in `turn` ask for a human?”, or “Read `history` to know what words like it stand for.” `turn` holds every transcript of the turn, joined with a space. The [`history`](/docs/server/classifier#options) option of the server sets how many turns before it come along. To send more, pass `state`. It receives the input, and returns what Jev reads, the input with your own fields next to it for instance: ``` new TypesafeClassifier({ questions, state: (input) => ({ ...(input as object), customer: { plan: 'Fiber 1 Gb', outageInArea: true }, }),}) ``` The questions can then point at `customer` as well. ## Questions Three helpers, re-exported from the TypeSafe SDK, build the questions. The key of each question names its answer. Helper Answers Example `choice(instructions, labels)` One label out of several The intent, the topic, the language `score(instructions, rubric)` A position on an ordered scale, from zero Frustration, urgency, how sure the user sounds `noul(instructions, criteria?)` The probability of a yes Asks for a human, wants to cancel `choice()` takes an object of labels, each with a description, or `null` to leave it undescribed. `score()` takes an array of at least two descriptions, from the lowest level up. `noul()` can describe what yes and no mean with `{ true, false }`. Ask every question in one request. Jev answers them in parallel, so a question that only matters now and then (a manipulation attempt, a known outage) costs little more to ask every time, and your code reads the answers it needs. TypeSafe calls this pattern a speculative fan-out. To pick the questions per input, pass a function. It receives the input: ``` import { MicdropTurnInput } from '@micdrop/server' new TypesafeClassifier({ // Asks the opening questions on the first turn of the user only questions: (input) => (input as MicdropTurnInput).history.some((item) => item.role === 'user') ? questions : { ...questions, ...openingQuestions },}) ``` ## Reading the answers The result is the `SystemOneResult` of the TypeSafe SDK, typed from your questions: ``` const { answers, usage } = getTurnClassification(this.conversation)!.result answers.intent.choice // 'billing', typed as one of your labelsanswers.intent.confidence // 0.92answers.intent.probabilities // { billing: 0.92, outage: 0.03, cancel: 0.04, other: 0.01 } answers.frustration.score // 1.4, the expected score, between two levelsanswers.frustration.probabilities // { 0: 0.1, 1: 0.4, 2: 0.5 } answers.wantsHuman.noul // 0.07, the probability of a yes usage.input_tokens // 412 ``` The probabilities are calibrated, so a threshold means what it says: route on `noul > 0.8` or `confidence > 0.6`, and let the LLM handle the turns below it. A `score` is an expectation over the rubric, so it can fall between two levels. On a rubric of four levels from calm to angry, `score > 2.5` reads as “closer to angry than to frustrated”. ## Options Option Type Default Description `apiKey` `string` `TYPESAFE_API_KEY` Your TypeSafe API key, read from the environment when left out `model` `string` `'jev-latest'` Model answering the questions `questions` `Questions | (input) => Questions` Required Questions built with `choice()`, `score()` and `noul()`, or a function of the input `state` `(input) => EntryType` The input Builds what Jev reads from the input, to add fields next to it `timeout` `number` `3000` Timeout of each request in ms When to wait for the result, whether to send it to the client and how much history to include are options of the server, in [`classifierOptions`](/docs/server/classifier#options). ## Events Event Payload Description `Classification` `MicdropClassification` Answers of Jev about an input, with their duration. See the [Classifier interface](/docs/ai-integration/custom-integrations/custom-classifier) for the full contract. ## Latency and price TypeSafe announces 70 to 500 ms end to end, depending on the length of the state and the number of questions. Measured on the real API in the Micdrop demos, with a turn and its history as the state, each request took about 250 to 700 ms. Input costs $0.042 per million tokens, and output is free. A request of a thousand tokens costs about $0.00004, so classifying every turn of a long call stays well under a cent. ## Limitations * Jev understands English best. Other languages work, with less accurate answers. * It reads text only, so the tone of the voice reaches it through the words alone. * The state and the longest question share a budget of 32k tokens. * It picks, scores and answers yes or no. Counting, extracting a value or writing text stays with the LLM, or with [extraction](/docs/server/extract). ## Demos The demos that run on Jev are listed with the other examples, in [Examples and demos](/docs/examples#classifier-demos). ## Documentation Read the [TypeSafe documentation](https://docs.typesafe.ai) for the questions, the models and the API. [Previous← Qwen3-TTS](/docs/ai-integration/provided-integrations/qwen-tts)[NextWhisper →](/docs/ai-integration/provided-integrations/whisper) On this page * [Installation](#installation) * [Usage with MicdropServer](#usage-with-micdropserver) * [Usage without MicdropServer](#usage-without-micdropserver) * [State](#state) * [Questions](#questions) * [Reading the answers](#reading-the-answers) * [Options](#options) * [Events](#events) * [Latency and price](#latency-and-price) * [Limitations](#limitations) * [Demos](#demos) * [Documentation](#documentation)