TTS / STT (Text-zu-Sprache / Sprache-zu-Text, AI SDK)

import { readFileSync, writeFileSync } from "node:fs";
import { phaseo } from "@phaseo/ai-sdk-provider";
import { experimental_generateSpeech, experimental_transcribe } from "ai";

const audioInput = readFileSync("./audio.mp3");

const transcription = await experimental_transcribe({
  model: phaseo.transcriptionModel("openai/whisper-1"),
  audioData: new Blob([audioInput], { type: "audio/mpeg" }),
});

console.log(transcription.text);
console.log(transcription.providerMetadata);

const speech = await experimental_generateSpeech({
  model: phaseo.speechModel("openai/tts-1"),
  text: "Hello from Phaseo audio.",
  voice: "alloy",
  outputFormat: "mp3",
});

writeFileSync("./speech.mp3", Buffer.from(speech.audio.uint8Array));
console.log(speech.providerMetadata);