Transcription temps réel

ffmpeg -i entree.mp3 -f s16le -ar 16000 -ac 1 sortie.pcm

import { mistralRealtimeTranscription } from "@ai_kit/core";
import { readFile } from "node:fs/promises";

const rt = mistralRealtimeTranscription({ apiKey: process.env.MISTRAL_API_KEY! });

// PCM s16le / 16 kHz / mono — par ex. produit par ffmpeg
const pcm = new Uint8Array(await readFile("audio.pcm"));

async function* chunks() {
  const size = 4096;
  for (let i = 0; i < pcm.length; i += size) {
    yield pcm.subarray(i, i + size);
  }
}

let full = "";
for await (const ev of rt.transcribeStream(chunks())) {
  if (ev.type === "delta") {
    full += ev.textDelta;
    process.stdout.write(ev.textDelta);
  } else if (ev.type === "done") {
    console.log("\nTerminé :", ev.text);
  }
}

import { mistralRealtimeTranscription } from "@ai_kit/core";

const rt = mistralRealtimeTranscription();
const session = await rt.connect({ targetStreamingDelayMs: 1000 });

// Lire les événements en parallèle
(async () => {
  for await (const ev of session) {
    if (ev.type === "delta") process.stdout.write(ev.textDelta);
    if (ev.type === "done") console.log("\n→", ev.text);
    if (ev.type === "error") console.error("Erreur :", ev.error);
  }
})();

// Pousser l'audio à mesure qu'il arrive
micro.on("data", (pcm: Uint8Array) => session.sendAudio(pcm)); // découpé auto > 256 Ko
micro.on("end", async () => {
  await session.flush();
  await session.end();
  await session.close();
});

type RealtimeTranscriptionEvent =
  | { type: "session.created"; session: { requestId; model; audioFormat } }
  | { type: "session.updated"; session: { requestId; model; audioFormat } }
  | { type: "delta"; textDelta: string }
  | { type: "segment"; text: string; startSecond?: number; endSecond?: number }
  | { type: "language"; language: string }
  | { type: "done"; text: string; usage?: { promptTokens?; completionTokens? } }
  | { type: "error"; error: string }
  | { type: "unknown"; raw: unknown };

import { createRealtimeTranscription } from "@ai_kit/core";

const rt = createRealtimeTranscription({
  modelId: "voxtral-mini-transcribe-realtime-2602",
  apiKey: process.env.MISTRAL_API_KEY!,
  baseURL: "https://api.mistral.ai/v1", // défaut ; http/https → ws/wss
  providerName: "mistral",              // défaut
});