refactor(channels): remove channel-side voice transcription (Phase 12)

Remove SetTranscriber and inline transcription logic from 4 channels
(Telegram, Discord, Slack, OneBot) and the gateway wiring. Voice/audio
files are still downloaded and stored in MediaStore with simple text
annotations ([voice], [audio: filename], [file: name]). The pkg/voice
package is preserved for future Agent-level transcription middleware.

cmd/picoclaw/internal/gateway/helpers.go

@@ -6,7 +6,6 @@ import (
 	"os"
 	"os/signal"
 	"path/filepath"
-	"strings"
 	"time"
 
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal"
@@ -14,14 +13,14 @@ import (
 	"github.com/sipeed/picoclaw/pkg/bus"
 	"github.com/sipeed/picoclaw/pkg/channels"
 	_ "github.com/sipeed/picoclaw/pkg/channels/dingtalk"
-	dch "github.com/sipeed/picoclaw/pkg/channels/discord"
+	_ "github.com/sipeed/picoclaw/pkg/channels/discord"
 	_ "github.com/sipeed/picoclaw/pkg/channels/feishu"
 	_ "github.com/sipeed/picoclaw/pkg/channels/line"
 	_ "github.com/sipeed/picoclaw/pkg/channels/maixcam"
 	_ "github.com/sipeed/picoclaw/pkg/channels/onebot"
 	_ "github.com/sipeed/picoclaw/pkg/channels/qq"
-	slackch "github.com/sipeed/picoclaw/pkg/channels/slack"
+	_ "github.com/sipeed/picoclaw/pkg/channels/slack"
-	tgramch "github.com/sipeed/picoclaw/pkg/channels/telegram"
+	_ "github.com/sipeed/picoclaw/pkg/channels/telegram"
 	_ "github.com/sipeed/picoclaw/pkg/channels/wecom"
 	_ "github.com/sipeed/picoclaw/pkg/channels/whatsapp"
 	"github.com/sipeed/picoclaw/pkg/config"
@@ -34,7 +33,6 @@ import (
 	"github.com/sipeed/picoclaw/pkg/providers"
 	"github.com/sipeed/picoclaw/pkg/state"
 	"github.com/sipeed/picoclaw/pkg/tools"
-	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 func gatewayCmd(debug bool) error {
@@ -127,42 +125,6 @@ func gatewayCmd(debug bool) error {
 	agentLoop.SetChannelManager(channelManager)
 	agentLoop.SetMediaStore(mediaStore)
 
-	var transcriber *voice.GroqTranscriber
-	groqAPIKey := cfg.Providers.Groq.APIKey
-	if groqAPIKey == "" {
-		for _, mc := range cfg.ModelList {
-			if strings.HasPrefix(mc.Model, "groq/") && mc.APIKey != "" {
-				groqAPIKey = mc.APIKey
-				break
-			}
-		}
-	}
-	if groqAPIKey != "" {
-		transcriber = voice.NewGroqTranscriber(groqAPIKey)
-		logger.InfoC("voice", "Groq voice transcription enabled")
-	}
-
-	if transcriber != nil {
-		if telegramChannel, ok := channelManager.GetChannel("telegram"); ok {
-			if tc, ok := telegramChannel.(*tgramch.TelegramChannel); ok {
-				tc.SetTranscriber(transcriber)
-				logger.InfoC("voice", "Groq transcription attached to Telegram channel")
-			}
-		}
-		if discordChannel, ok := channelManager.GetChannel("discord"); ok {
-			if dc, ok := discordChannel.(*dch.DiscordChannel); ok {
-				dc.SetTranscriber(transcriber)
-				logger.InfoC("voice", "Groq transcription attached to Discord channel")
-			}
-		}
-		if slackChannel, ok := channelManager.GetChannel("slack"); ok {
-			if sc, ok := slackChannel.(*slackch.SlackChannel); ok {
-				sc.SetTranscriber(transcriber)
-				logger.InfoC("voice", "Groq transcription attached to Slack channel")
-			}
-		}
-	}
-
 	enabledChannels := channelManager.GetEnabledChannels()
 	if len(enabledChannels) > 0 {
 		fmt.Printf("✓ Channels enabled: %s\n", enabledChannels)

pkg/channels/discord/discord.go

@@ -16,11 +16,9 @@ import (
 	"github.com/sipeed/picoclaw/pkg/logger"
 	"github.com/sipeed/picoclaw/pkg/media"
 	"github.com/sipeed/picoclaw/pkg/utils"
-	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 const (
-	transcriptionTimeout = 30 * time.Second
 	sendTimeout = 10 * time.Second
 )
 
@@ -28,7 +26,6 @@ type DiscordChannel struct {
 	*channels.BaseChannel
 	session    *discordgo.Session
 	config     config.DiscordConfig
-	transcriber *voice.GroqTranscriber
 	ctx        context.Context
 	cancel     context.CancelFunc
 	typingMu   sync.Mutex
@@ -48,16 +45,11 @@ func NewDiscordChannel(cfg config.DiscordConfig, bus *bus.MessageBus) (*DiscordC
 		BaseChannel: base,
 		session:     session,
 		config:      cfg,
-		transcriber: nil,
 		ctx:         context.Background(),
 		typingStop:  make(map[string]chan struct{}),
 	}, nil
 }
 
-func (c *DiscordChannel) SetTranscriber(transcriber *voice.GroqTranscriber) {
-	c.transcriber = transcriber
-}
-
 func (c *DiscordChannel) Start(ctx context.Context) error {
 	logger.InfoC("discord", "Starting Discord bot")
 
@@ -265,7 +257,7 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag
 		return
 	}
 
-	// Check allowlist first to avoid downloading attachments and transcribing for rejected users
+	// Check allowlist first to avoid downloading attachments for rejected users
 	if !c.IsAllowed(m.Author.ID) {
 		logger.DebugCF("discord", "Message rejected by allowlist", map[string]any{
 			"user_id": m.Author.ID,
@@ -323,29 +315,8 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag
 		if isAudio {
 			localPath := c.downloadAttachment(attachment.URL, attachment.Filename)
 			if localPath != "" {
-				transcribedText := ""
-				if c.transcriber != nil && c.transcriber.IsAvailable() {
-					ctx, cancel := context.WithTimeout(c.ctx, transcriptionTimeout)
-					result, err := c.transcriber.Transcribe(ctx, localPath)
-					cancel() // Release context resources immediately to avoid leaks in for loop
-
-					if err != nil {
-						logger.ErrorCF("discord", "Voice transcription failed", map[string]any{
-							"error": err.Error(),
-						})
-						transcribedText = fmt.Sprintf("[audio: %s (transcription failed)]", attachment.Filename)
-					} else {
-						transcribedText = fmt.Sprintf("[audio transcription: %s]", result.Text)
-						logger.DebugCF("discord", "Audio transcribed successfully", map[string]any{
-							"text": result.Text,
-						})
-					}
-				} else {
-					transcribedText = fmt.Sprintf("[audio: %s]", attachment.Filename)
-				}
-
 				mediaPaths = append(mediaPaths, storeMedia(localPath, attachment.Filename))
-				content = appendContent(content, transcribedText)
+				content = appendContent(content, fmt.Sprintf("[audio: %s]", attachment.Filename))
 			} else {
 				logger.WarnCF("discord", "Failed to download audio attachment", map[string]any{
 					"url":      attachment.URL,

pkg/channels/onebot/onebot.go

@@ -18,7 +18,6 @@ import (
 	"github.com/sipeed/picoclaw/pkg/logger"
 	"github.com/sipeed/picoclaw/pkg/media"
 	"github.com/sipeed/picoclaw/pkg/utils"
-	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 type OneBotChannel struct {
@@ -36,7 +35,6 @@ type OneBotChannel struct {
 	selfID          int64
 	pending         map[string]chan json.RawMessage
 	pendingMu       sync.Mutex
-	transcriber     *voice.GroqTranscriber
 	lastMessageID   sync.Map
 	pendingEmojiMsg sync.Map
 }
@@ -112,10 +110,6 @@ func NewOneBotChannel(cfg config.OneBotConfig, messageBus *bus.MessageBus) (*One
 	}, nil
 }
 
-func (c *OneBotChannel) SetTranscriber(transcriber *voice.GroqTranscriber) {
-	c.transcriber = transcriber
-}
-
 func (c *OneBotChannel) setMsgEmojiLike(messageID string, emojiID int, set bool) {
 	go func() {
 		_, err := c.sendAPIRequest("set_msg_emoji_like", map[string]any{
@@ -794,28 +788,11 @@ func (c *OneBotChannel) parseMessageSegments(
 						LoggerPrefix: "onebot",
 					})
 					if localPath != "" {
-						if c.transcriber != nil && c.transcriber.IsAvailable() {
-							tctx, tcancel := context.WithTimeout(c.ctx, 30*time.Second)
-							result, err := c.transcriber.Transcribe(tctx, localPath)
-							tcancel()
-							if err != nil {
-								logger.WarnCF("onebot", "Voice transcription failed", map[string]any{
-									"error": err.Error(),
-								})
-								textParts = append(textParts, "[voice (transcription failed)]")
-								mediaRefs = append(mediaRefs, storeFile(localPath, "voice.amr"))
-							} else {
-								textParts = append(textParts, fmt.Sprintf("[voice transcription: %s]", result.Text))
-								// Still store the file so it can be released later
-								storeFile(localPath, "voice.amr")
-							}
-						} else {
 						textParts = append(textParts, "[voice]")
 						mediaRefs = append(mediaRefs, storeFile(localPath, "voice.amr"))
 					}
 				}
 			}
-			}
 
 		case "reply":
 			if data != nil {

pkg/channels/slack/slack.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"strings"
 	"sync"
-	"time"
 
 	"github.com/slack-go/slack"
 	"github.com/slack-go/slack/slackevents"
@@ -17,7 +16,6 @@ import (
 	"github.com/sipeed/picoclaw/pkg/logger"
 	"github.com/sipeed/picoclaw/pkg/media"
 	"github.com/sipeed/picoclaw/pkg/utils"
-	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 type SlackChannel struct {
@@ -27,7 +25,6 @@ type SlackChannel struct {
 	socketClient *socketmode.Client
 	botUserID    string
 	teamID       string
-	transcriber  *voice.GroqTranscriber
 	ctx          context.Context
 	cancel       context.CancelFunc
 	pendingAcks  sync.Map
@@ -60,10 +57,6 @@ func NewSlackChannel(cfg config.SlackConfig, messageBus *bus.MessageBus) (*Slack
 	}, nil
 }
 
-func (c *SlackChannel) SetTranscriber(transcriber *voice.GroqTranscriber) {
-	c.transcriber = transcriber
-}
-
 func (c *SlackChannel) Start(ctx context.Context) error {
 	logger.InfoC("slack", "Starting Slack channel (Socket Mode)")
 
@@ -311,23 +304,9 @@ func (c *SlackChannel) handleMessageEvent(ev *slackevents.MessageEvent) {
 				continue
 			}
 			mediaPaths = append(mediaPaths, storeMedia(localPath, file.Name))
-
-			if utils.IsAudioFile(file.Name, file.Mimetype) && c.transcriber != nil && c.transcriber.IsAvailable() {
-				ctx, cancel := context.WithTimeout(c.ctx, 30*time.Second)
-				defer cancel()
-				result, err := c.transcriber.Transcribe(ctx, localPath)
-
-				if err != nil {
-					logger.ErrorCF("slack", "Voice transcription failed", map[string]any{"error": err.Error()})
-					content += fmt.Sprintf("\n[audio: %s (transcription failed)]", file.Name)
-				} else {
-					content += fmt.Sprintf("\n[voice transcription: %s]", result.Text)
-				}
-			} else {
 			content += fmt.Sprintf("\n[file: %s]", file.Name)
 		}
 	}
-	}
 
 	if strings.TrimSpace(content) == "" {
 		return

pkg/channels/telegram/telegram.go

@@ -22,7 +22,6 @@ import (
 	"github.com/sipeed/picoclaw/pkg/logger"
 	"github.com/sipeed/picoclaw/pkg/media"
 	"github.com/sipeed/picoclaw/pkg/utils"
-	"github.com/sipeed/picoclaw/pkg/voice"
 )
 
 type TelegramChannel struct {
@@ -32,7 +31,6 @@ type TelegramChannel struct {
 	commands     TelegramCommander
 	config       *config.Config
 	chatIDs      map[string]int64
-	transcriber  *voice.GroqTranscriber
 	ctx          context.Context
 	cancel       context.CancelFunc
 	placeholders sync.Map // chatID -> messageID
@@ -91,16 +89,11 @@ func NewTelegramChannel(cfg *config.Config, bus *bus.MessageBus) (*TelegramChann
 		bot:          bot,
 		config:       cfg,
 		chatIDs:      make(map[string]int64),
-		transcriber:  nil,
 		placeholders: sync.Map{},
 		stopThinking: sync.Map{},
 	}, nil
 }
 
-func (c *TelegramChannel) SetTranscriber(transcriber *voice.GroqTranscriber) {
-	c.transcriber = transcriber
-}
-
 func (c *TelegramChannel) Start(ctx context.Context) error {
 	logger.InfoC("telegram", "Starting Telegram bot (polling mode)...")
 
@@ -391,32 +384,10 @@ func (c *TelegramChannel) handleMessage(ctx context.Context, message *telego.Mes
 		if voicePath != "" {
 			mediaPaths = append(mediaPaths, storeMedia(voicePath, "voice.ogg"))
 
-			transcribedText := ""
-			if c.transcriber != nil && c.transcriber.IsAvailable() {
-				transcriberCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
-				defer cancel()
-
-				result, err := c.transcriber.Transcribe(transcriberCtx, voicePath)
-				if err != nil {
-					logger.ErrorCF("telegram", "Voice transcription failed", map[string]any{
-						"error": err.Error(),
-						"path":  voicePath,
-					})
-					transcribedText = "[voice (transcription failed)]"
-				} else {
-					transcribedText = fmt.Sprintf("[voice transcription: %s]", result.Text)
-					logger.InfoCF("telegram", "Voice transcribed successfully", map[string]any{
-						"text": result.Text,
-					})
-				}
-			} else {
-				transcribedText = "[voice]"
-			}
-
 			if content != "" {
 				content += "\n"
 			}
-			content += transcribedText
+			content += "[voice]"
 		}
 	}