famapp/src/lib/llm/transcribe.ts

import { getLlmConfig } from "./config";

const MAX_AUDIO_BYTES = 25 * 1024 * 1024;

export async function transcribeAudioFile(file: File | Blob, filename: string): Promise<string> {
  if (file.size > MAX_AUDIO_BYTES) {
    throw new Error("Recording exceeds 25 MB limit");
  }

  const config = getLlmConfig();
  if (config.provider === "mock" || !config.baseUrl) {
    return "add milk to the shopping list";
  }

  const formData = new FormData();
  formData.append("file", file, filename);
  formData.append("model", "whisper-1");

  const url = `${config.baseUrl.replace(/\/$/, "")}/audio/transcriptions`;
  const headers: Record<string, string> = {};
  if (config.apiKey) {
    headers.Authorization = `Bearer ${config.apiKey}`;
  }

  const response = await fetch(url, {
    method: "POST",
    headers,
    body: formData,
  });

  if (!response.ok) {
    const detail = await response.text();
    throw new Error(`Transcription failed (${response.status}): ${detail.slice(0, 400)}`);
  }

  const contentType = response.headers.get("content-type") ?? "";
  if (contentType.includes("application/json")) {
    const payload = (await response.json()) as { text?: string };
    const text = payload.text?.trim();
    if (!text) throw new Error("Transcription returned empty text");
    return text;
  }

  const text = (await response.text()).trim();
  if (!text) throw new Error("Transcription returned empty text");
  return text;
}