- audio.StemSeparator/StemSeparationProvider: Demucs zip transport via
  POST /upstream/<id>/v1/stems (Mode two -> two_stems=vocals; model +
  format fields); bounded zip unpack, entry name -> stem, ext -> MIME.
- SFXModel reuses musicgen against the sync /upstream/<id>/v1/sfx route
  (JSON prompt/seconds/steps/cfg_scale/seed -> WAV); musicgen.Request
  gains CFGScale.
- audio.SpeechEnhancer/SpeechEnhancementProvider:
  POST /upstream/<id>/v1/enhance -> WAV (result reuses SpeechResult).
- SpeechRequest.ReferenceAudio/ReferenceMIME (+WithReferenceAudio):
  llamaswap switches to the chatterbox clone route
  POST /upstream/<id>/v1/audio/speech/upload (input + voice_file),
  wav MIME fallback.
- TranscriptionRequest.Translate (+WithTranslate): translate=true form
  field, language=auto forced when no explicit hint (whisper.cpp default
  en would skip translation).
- httptest contract tests (zip unpack, clone-route switch, translate +
  auto-language injection); ADR-0024 (index row deferred — MJ-A backfills
  the ADR index table and parallel edits would conflict).

Co-Authored-By: Claude Fable 5 <[email protected]>

@@ -0,0 +41,4 @@
+
+// SpeechEnhancerModelOption configures a SpeechEnhancer at construction time.
+// Reserved for future per-model settings.
+type SpeechEnhancerModelOption func(*SpeechEnhancerModelConfig)

@@ -75,0 +88,4 @@
+// the JSON route's mp3) when neither the response header nor the requested
+// format decides.
+func (m *speechModel) speakWithReference(ctx context.Context, req audio.SpeechRequest) (*audio.SpeechResult, error) {
+	path, err := upstreamPath(m.id, "/v1/audio/speech/upload")

@@ -75,0 +107,4 @@
+	if err != nil {
+		return nil, err
+	}
+	audioBytes, contentType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, formType, body, maxResponseBytes)

@@ -75,0 +114,4 @@
+	if len(audioBytes) == 0 {
+		return nil, &llm.APIError{Provider: m.p.name, Model: m.id, Message: "speech clone response contained no audio"}
+	}
+	mimeType := "audio/wav"

@@ -0,0 +28,4 @@
+		gotRef, _ = io.ReadAll(f)
+		gotFilename = hdr.Filename
+		w.Header().Set("Content-Type", "audio/wav")
+		_, _ = w.Write(wavFixture())

@@ -0,0 +45,4 @@
+	if err != nil {
+		return nil, err
+	}
+	raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxResponseBytes)

@@ -0,0 +52,4 @@
+	if len(raw) == 0 {
+		return nil, &llm.APIError{Provider: m.p.name, Model: m.id, Message: "enhance response contained no audio"}
+	}
+	mimeType := audioResultMIME(respType, raw)

@@ -0,0 +102,4 @@
+// audioResultMIME resolves an audio body's MIME type: the response
+// Content-Type when it is a concrete audio type, else content sniffing
+// (RIFF/WAVE and friends), else "" — the caller treats undetectable as an
+// upstream error, mirroring videoMIME. Sniffed "audio/wave" is normalized

@@ -0,0 +25,4 @@
+// maxStemsResponseBytes caps the /v1/stems zip body: four WAV stems of a
+// long song legitimately pass the 64MB JSON cap. Bounded so a buggy
+// upstream can't allocate without limit.
+const maxStemsResponseBytes = 512 << 20

@@ -0,0 +71,4 @@
+		twoStems = "vocals"
+	}
+	body, contentType, err := buildMultipart("build stems form",
+		filePart{field: "file", filename: transcriptionFilename(req.Filename, req.MIME), data: req.Audio},

@@ -0,0 +94,4 @@
+		return nil, &llm.APIError{Provider: m.p.name, Model: m.id,
+			Message: fmt.Sprintf("stems response is not a zip (Content-Type %q): %s", respType, truncateForError(raw))}
+	}
+	res := &audio.StemSeparationResult{}

@@ -0,0 +171,4 @@
+
+// wavFixture is a minimal RIFF/WAVE header so http.DetectContentType sniffs
+// audio/wave.
+func wavFixture() []byte {