Cyrene_v2/internal/services/gateway/audio.go

package gateway

import (
	"encoding/json"
	"net/http"
	"strconv"
	"strings"

	apperr "git.yeij.top/AskaEth/Cyrene_v2/internal/errors"
	"git.yeij.top/AskaEth/Cyrene_v2/internal/runtime/multimodal/voice"
)

// maxAudioRequestBytes caps the JSON body a /api/v1/audio/* request may carry so
// a huge base64 audio payload cannot exhaust memory.
const maxAudioRequestBytes = 32 << 20

// transcribeRequest is the POST /api/v1/audio/transcribe body. Audio is a base64
// (or data: URI) blob; Format is its encoding ("wav"/"mp3"/"ogg").
type transcribeRequest struct {
	Audio    string `json:"audio"`
	Format   string `json:"format"`
	DeviceID string `json:"deviceId,omitempty"`
}

// speechRequest is the POST /api/v1/audio/speech body. Voice/format are accepted
// for forward compatibility; synthesis currently follows the server's
// VOICE_TTS_VOICE_ID / VOICE_TTS_FORMAT config. Instruction is an optional
// per-request emotion/tone override for a cloned voice (声音复刻); a system voice
// (longxiaochun_v3) ignores it and never receives a free-form instruction.
type speechRequest struct {
	Text        string `json:"text"`
	Voice       string `json:"voice,omitempty"`
	Format      string `json:"format,omitempty"`
	Instruction string `json:"instruction,omitempty"`
}

// handleTranscribe runs STT on the uploaded audio and returns the recognized
// text. It is the REST source for native clients, bypassing the 4KB WebSocket
// frame limit that would truncate a base64 audio blob.
func (s *Server) handleTranscribe(w http.ResponseWriter, r *http.Request) {
	r.Body = http.MaxBytesReader(w, r.Body, maxAudioRequestBytes)
	var req transcribeRequest
	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
		s.auditClaims(r, "audio.transcribe", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "invalid request body"))
		return
	}
	if s.voice == nil {
		s.auditClaims(r, "audio.transcribe", "error")
		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_unavailable", "voice service is not configured"))
		return
	}
	audio, err := decodeVoiceAudio(req.Audio, req.Format)
	if err != nil {
		s.auditClaims(r, "audio.transcribe", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "audio could not be decoded"))
		return
	}
	if len(audio.Data) == 0 {
		s.auditClaims(r, "audio.transcribe", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "audio is required"))
		return
	}
	text, rung, err := sttWithProvider(r.Context(), s.voice, audio)
	if err != nil {
		s.auditClaims(r, "audio.transcribe", "error")
		s.log.Warn("voice transcribe", "err", err)
		writeError(w, apperr.Wrap(apperr.ErrInternal, "stt_failed", "speech transcription failed"))
		return
	}
	s.auditClaims(r, "audio.transcribe", "ok")
	out := map[string]any{"text": text}
	if sig := providerSignal(rung, strings.TrimSpace(text) == ""); sig != "" {
		out["provider"] = sig
	}
	writeJSON(w, http.StatusOK, out)
}

// handleSpeech synthesizes speech for the given text and writes the raw audio
// bytes (audio/<format>) back — a binary response, not a JSON envelope.
func (s *Server) handleSpeech(w http.ResponseWriter, r *http.Request) {
	r.Body = http.MaxBytesReader(w, r.Body, maxAudioRequestBytes)
	var req speechRequest
	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
		s.auditClaims(r, "audio.speech", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "invalid request body"))
		return
	}
	if strings.TrimSpace(req.Text) == "" {
		s.auditClaims(r, "audio.speech", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "text is required"))
		return
	}
	if s.voice == nil {
		s.auditClaims(r, "audio.speech", "error")
		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_unavailable", "voice service is not configured"))
		return
	}
	ctx := r.Context()
	if req.Instruction != "" {
		ctx = voice.WithTTSInstruction(ctx, req.Instruction)
	}
	audi, rung, err := ttsWithProvider(ctx, s.voice, req.Text)
	if err != nil {
		s.auditClaims(r, "audio.speech", "error")
		s.log.Warn("voice speech", "err", err)
		writeError(w, apperr.Wrap(apperr.ErrInternal, "tts_failed", "speech synthesis failed"))
		return
	}
	if len(audi.Data) == 0 {
		s.auditClaims(r, "audio.speech", "error")
		w.Header().Set(voiceProviderHeader, providerSignal(rung, true))
		writeError(w, apperr.Wrap(apperr.ErrInternal, "tts_empty", "no audio synthesized"))
		return
	}
	s.auditClaims(r, "audio.speech", "ok")
	w.Header().Set("Content-Type", audioMime(audi.Format))
	w.Header().Set("Content-Length", strconv.Itoa(len(audi.Data)))
	w.WriteHeader(http.StatusOK)
	_, _ = w.Write(audi.Data)
}

// voiceCloneRequest is the POST /api/v1/audio/voice-clone body. URL is the public
// reference audio URL; prefix is the optional voice-name prefix (≤10 alnum chars).
// Neither is logged, and the URL is not persisted (owner + audit only, red line).
type voiceCloneRequest struct {
	URL    string `json:"url"`
	Prefix string `json:"prefix,omitempty"`
}

// handleVoiceClone creates a custom TTS voice from a public reference audio URL
// via the Bailian voice-enrollment API (声音复刻 create_voice) and returns the new
// voice_id. Owner-only + audited; the reference URL is never written to the audit
// trail or the log (red line).
func (s *Server) handleVoiceClone(w http.ResponseWriter, r *http.Request) {
	r.Body = http.MaxBytesReader(w, r.Body, maxAudioRequestBytes)
	var req voiceCloneRequest
	if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
		s.auditClaims(r, "audio.voice-clone", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "invalid request body"))
		return
	}
	if strings.TrimSpace(req.URL) == "" {
		s.auditClaims(r, "audio.voice-clone", "error")
		writeError(w, apperr.Wrap(apperr.ErrBadRequest, "bad_request", "url is required"))
		return
	}
	if s.voice == nil {
		s.auditClaims(r, "audio.voice-clone", "error")
		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_unavailable", "voice service is not configured"))
		return
	}
	voiceID, err := s.voice.CloneVoice(r.Context(), req.URL, req.Prefix)
	if err != nil {
		s.auditClaims(r, "audio.voice-clone", "error")
		// Do not log the cause: a provider error body may echo the reference URL.
		s.log.Warn("voice clone failed")
		writeError(w, apperr.Wrap(apperr.ErrInternal, "voice_clone_failed", "voice clone failed"))
		return
	}
	s.auditClaims(r, "audio.voice-clone", "ok")
	writeJSON(w, http.StatusOK, map[string]any{"voiceId": voiceID})
}

// audioMime maps an audio format to its Content-Type for the speech response.
func audioMime(format string) string {
	switch strings.ToLower(format) {
	case "mp3", "mpeg":
		return "audio/mpeg"
	case "ogg", "oga":
		return "audio/ogg"
	case "webm":
		return "audio/webm"
	default:
		return "audio/wav"
	}
}