Fix voice transcription

pkg/agent/loop.go

@@ -18,6 +18,8 @@ import (
 	"time"
 	"unicode/utf8"
 
+	"regexp"
+
 	"github.com/sipeed/picoclaw/pkg/bus"
 	"github.com/sipeed/picoclaw/pkg/channels"
 	"github.com/sipeed/picoclaw/pkg/config"
@@ -30,6 +32,7 @@ import (
 	"github.com/sipeed/picoclaw/pkg/state"
 	"github.com/sipeed/picoclaw/pkg/tools"
 	"github.com/sipeed/picoclaw/pkg/utils"
+	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 type AgentLoop struct {
@@ -42,6 +45,7 @@ type AgentLoop struct {
 	fallback       *providers.FallbackChain
 	channelManager *channels.Manager
 	mediaStore     media.MediaStore
+	transcriber    voice.Transcriber
 }
 
 // processOptions configures how a message is processed
@@ -262,6 +266,64 @@ func (al *AgentLoop) SetMediaStore(s media.MediaStore) {
 	al.mediaStore = s
 }
 
+// SetTranscriber injects a voice transcriber for agent-level audio transcription.
+func (al *AgentLoop) SetTranscriber(t voice.Transcriber) {
+	al.transcriber = t
+}
+
+var audioAnnotationRe = regexp.MustCompile(`\[(voice|audio)(?::[^\]]*)?\]`)
+
+// transcribeAudioInMessage resolves audio media refs, transcribes them, and
+// replaces audio annotations in msg.Content with the transcribed text.
+func (al *AgentLoop) transcribeAudioInMessage(ctx context.Context, msg bus.InboundMessage) bus.InboundMessage {
+	if al.transcriber == nil || !al.transcriber.IsAvailable() || al.mediaStore == nil || len(msg.Media) == 0 {
+		return msg
+	}
+
+	// Transcribe each audio media ref in order.
+	var transcriptions []string
+	for _, ref := range msg.Media {
+		path, meta, err := al.mediaStore.ResolveWithMeta(ref)
+		if err != nil {
+			logger.WarnCF("voice", "Failed to resolve media ref", map[string]any{"ref": ref, "error": err})
+			continue
+		}
+		if !utils.IsAudioFile(meta.Filename, meta.ContentType) {
+			continue
+		}
+		result, err := al.transcriber.Transcribe(ctx, path)
+		if err != nil {
+			logger.WarnCF("voice", "Transcription failed", map[string]any{"ref": ref, "error": err})
+			transcriptions = append(transcriptions, "")
+			continue
+		}
+		transcriptions = append(transcriptions, result.Text)
+	}
+
+	if len(transcriptions) == 0 {
+		return msg
+	}
+
+	// Replace audio annotations sequentially with transcriptions.
+	idx := 0
+	newContent := audioAnnotationRe.ReplaceAllStringFunc(msg.Content, func(match string) string {
+		if idx >= len(transcriptions) {
+			return match
+		}
+		text := transcriptions[idx]
+		idx++
+		return "[voice: " + text + "]"
+	})
+
+	// Append any remaining transcriptions not matched by an annotation.
+	for ; idx < len(transcriptions); idx++ {
+		newContent += "\n[voice: " + transcriptions[idx] + "]"
+	}
+
+	msg.Content = newContent
+	return msg
+}
+
 // inferMediaType determines the media type ("image", "audio", "video", "file")
 // from a filename and MIME content type.
 func inferMediaType(filename, contentType string) string {
@@ -364,6 +426,8 @@ func (al *AgentLoop) processMessage(ctx context.Context, msg bus.InboundMessage)
 			"session_key": msg.SessionKey,
 		})
 
+	msg = al.transcribeAudioInMessage(ctx, msg)
+
 	// Route system messages to processSystemMessage
 	if msg.Channel == "system" {
 		return al.processSystemMessage(ctx, msg)

pkg/voice/transcriber.go

@@ -16,6 +16,11 @@ import (
 	"github.com/sipeed/picoclaw/pkg/utils"
 )
 
+type Transcriber interface {
+	Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error)
+	IsAvailable() bool
+}
+
 type GroqTranscriber struct {
 	apiKey     string
 	apiBase    string

pkg/voice/transcriber_test.go

@@ -0,0 +1,97 @@
+package voice
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+// Ensure GroqTranscriber satisfies the Transcriber interface at compile time.
+var _ Transcriber = (*GroqTranscriber)(nil)
+
+func TestIsAvailable(t *testing.T) {
+	tests := []struct {
+		name   string
+		apiKey string
+		want   bool
+	}{
+		{"with key", "sk-test-key", true},
+		{"empty key", "", false},
+	}
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			tr := NewGroqTranscriber(tc.apiKey)
+			if got := tr.IsAvailable(); got != tc.want {
+				t.Errorf("IsAvailable() = %v, want %v", got, tc.want)
+			}
+		})
+	}
+}
+
+func TestTranscribe(t *testing.T) {
+	// Write a minimal fake audio file so the transcriber can open and send it.
+	tmpDir := t.TempDir()
+	audioPath := filepath.Join(tmpDir, "clip.ogg")
+	if err := os.WriteFile(audioPath, []byte("fake-audio-data"), 0o644); err != nil {
+		t.Fatalf("failed to write fake audio file: %v", err)
+	}
+
+	t.Run("success", func(t *testing.T) {
+		srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			if r.URL.Path != "/audio/transcriptions" {
+				t.Errorf("unexpected path: %s", r.URL.Path)
+			}
+			if r.Header.Get("Authorization") != "Bearer sk-test" {
+				t.Errorf("unexpected Authorization header: %s", r.Header.Get("Authorization"))
+			}
+			w.Header().Set("Content-Type", "application/json")
+			_ = json.NewEncoder(w).Encode(TranscriptionResponse{
+				Text:     "hello world",
+				Language: "en",
+				Duration: 1.5,
+			})
+		}))
+		defer srv.Close()
+
+		tr := NewGroqTranscriber("sk-test")
+		tr.apiBase = srv.URL
+
+		resp, err := tr.Transcribe(context.Background(), audioPath)
+		if err != nil {
+			t.Fatalf("Transcribe() error: %v", err)
+		}
+		if resp.Text != "hello world" {
+			t.Errorf("Text = %q, want %q", resp.Text, "hello world")
+		}
+		if resp.Language != "en" {
+			t.Errorf("Language = %q, want %q", resp.Language, "en")
+		}
+	})
+
+	t.Run("api error", func(t *testing.T) {
+		srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+			http.Error(w, `{"error":"invalid_api_key"}`, http.StatusUnauthorized)
+		}))
+		defer srv.Close()
+
+		tr := NewGroqTranscriber("sk-bad")
+		tr.apiBase = srv.URL
+
+		_, err := tr.Transcribe(context.Background(), audioPath)
+		if err == nil {
+			t.Fatal("expected error for non-200 response, got nil")
+		}
+	})
+
+	t.Run("missing file", func(t *testing.T) {
+		tr := NewGroqTranscriber("sk-test")
+		_, err := tr.Transcribe(context.Background(), filepath.Join(tmpDir, "nonexistent.ogg"))
+		if err == nil {
+			t.Fatal("expected error for missing file, got nil")
+		}
+	})
+}