d3ro-voice/server/supabase/functions/stt-proxy/index.ts

// server/supabase/functions/stt-proxy/index.ts
// Google Cloud Speech-to-Text 프록시.
// 요청: multipart/form-data (audio + sample_rate + language_code)
// 응답: { transcript, confidence, language_code, duration_seconds }

import { corsHeaders, handleCorsPreflightRequest } from '../_shared/cors.ts'
import { requireUser, authErrorResponse, type AuthError } from '../_shared/auth.ts'
import { checkQuota, consumeQuota, createServiceRoleClient } from '../_shared/quota.ts'

interface SttResult {
  transcript: string
  confidence: number
  language_code: string
  duration_seconds: number
}

// @ts-expect-error — Deno 런타임 전역
Deno.serve(async (req: Request) => {
  const preflight = handleCorsPreflightRequest(req)
  if (preflight) return preflight

  if (req.method !== 'POST') {
    return new Response(JSON.stringify({ error: 'Method not allowed' }), {
      status: 405,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' }
    })
  }

  try {
    // 1) 인증
    const user = await requireUser(req)

    // 2) 쿼터 체크
    const serviceClient = createServiceRoleClient()
    const quota = await checkQuota(user.id, 'stt_transcribe', serviceClient)
    if (!quota.allowed) {
      return new Response(
        JSON.stringify({
          error: 'quota_exceeded',
          current: quota.current,
          limit: quota.limit,
          tier: quota.tier
        }),
        {
          status: 429,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' }
        }
      )
    }

    // 3) 입력 파싱
    const formData = await req.formData()
    const audio = formData.get('audio')
    const sampleRate = Number(formData.get('sample_rate') ?? 16000)
    const languageCode = String(formData.get('language_code') ?? 'ko-KR')

    if (!(audio instanceof Blob)) {
      return new Response(JSON.stringify({ error: 'Missing audio field' }), {
        status: 400,
        headers: { ...corsHeaders, 'Content-Type': 'application/json' }
      })
    }

    // 4) Google Cloud STT 호출 — placeholder
    //
    // 실제 구현 시:
    //   const audioBytes = new Uint8Array(await audio.arrayBuffer())
    //   const base64Audio = btoa(String.fromCharCode(...audioBytes))
    //   const gcpKey = Deno.env.get('GOOGLE_CLOUD_STT_KEY')!
    //   const response = await fetch(
    //     `https://speech.googleapis.com/v1/speech:recognize?key=${gcpKey}`,
    //     {
    //       method: 'POST',
    //       headers: { 'Content-Type': 'application/json' },
    //       body: JSON.stringify({
    //         config: {
    //           encoding: 'LINEAR16',
    //           sampleRateHertz: sampleRate,
    //           languageCode,
    //           enableAutomaticPunctuation: true
    //         },
    //         audio: { content: base64Audio }
    //       })
    //     }
    //   )
    //   const data = await response.json()
    //   const transcript = data.results?.[0]?.alternatives?.[0]?.transcript ?? ''
    //   const confidence = data.results?.[0]?.alternatives?.[0]?.confidence ?? 0
    //
    // 스캐폴딩 단계에서는 placeholder 응답.

    const placeholder: SttResult = {
      transcript: '[stt-proxy placeholder — Google Cloud STT not yet wired]',
      confidence: 0,
      language_code: languageCode,
      duration_seconds: (audio.size / sampleRate / 2)  // 16-bit mono 가정
    }

    // 5) 쿼터 소비
    await consumeQuota(user.id, 'stt_transcribe', serviceClient, quota.limit)

    return new Response(JSON.stringify(placeholder), {
      status: 200,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' }
    })
  } catch (err) {
    if (err && typeof err === 'object' && 'status' in err && 'message' in err) {
      return authErrorResponse(err as AuthError, corsHeaders)
    }
    const message = err instanceof Error ? err.message : 'Unknown error'
    return new Response(JSON.stringify({ error: message }), {
      status: 500,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' }
    })
  }
})