* Discord & Telegram support ASR through groq

2026-02-10 17:10:41 +08:00
parent 24d5e833ad
commit 9936dbce52
7 changed files with 250 additions and 34 deletions
--- a/pkg/channels/discord.go
+++ b/pkg/channels/discord.go
@@ -3,17 +3,26 @@ package channels
 import (
 	"context"
 	"fmt"
+	"io"
+	"log"
+	"net/http"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"

 	"github.com/bwmarrin/discordgo"
 	"github.com/sipeed/picoclaw/pkg/bus"
 	"github.com/sipeed/picoclaw/pkg/config"
 	"github.com/sipeed/picoclaw/pkg/logger"
+	"github.com/sipeed/picoclaw/pkg/voice"
 )

 type DiscordChannel struct {
 	*BaseChannel
-	session *discordgo.Session
-	config  config.DiscordConfig
+	session     *discordgo.Session
+	config      config.DiscordConfig
+	transcriber *voice.GroqTranscriber
 }

 func NewDiscordChannel(cfg config.DiscordConfig, bus *bus.MessageBus) (*DiscordChannel, error) {
@@ -28,9 +37,14 @@ func NewDiscordChannel(cfg config.DiscordConfig, bus *bus.MessageBus) (*DiscordC
 		BaseChannel: base,
 		session:     session,
 		config:      cfg,
+		transcriber: nil,
 	}, 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")

@@ -103,11 +117,48 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag
 	mediaPaths := []string{}

 	for _, attachment := range m.Attachments {
-		mediaPaths = append(mediaPaths, attachment.URL)
-		if content != "" {
-			content += "\n"
+		isAudio := isAudioFile(attachment.Filename, attachment.ContentType)
+
+		if isAudio {
+			localPath := c.downloadAttachment(attachment.URL, attachment.Filename)
+			if localPath != "" {
+				mediaPaths = append(mediaPaths, localPath)
+
+				transcribedText := ""
+				if c.transcriber != nil && c.transcriber.IsAvailable() {
+					ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+					defer cancel()
+
+					result, err := c.transcriber.Transcribe(ctx, localPath)
+					if err != nil {
+						log.Printf("Voice transcription failed: %v", err)
+						transcribedText = fmt.Sprintf("[audio: %s (transcription failed)]", localPath)
+					} else {
+						transcribedText = fmt.Sprintf("[audio transcription: %s]", result.Text)
+						log.Printf("Audio transcribed successfully: %s", result.Text)
+					}
+				} else {
+					transcribedText = fmt.Sprintf("[audio: %s]", localPath)
+				}
+
+				if content != "" {
+					content += "\n"
+				}
+				content += transcribedText
+			} else {
+				mediaPaths = append(mediaPaths, attachment.URL)
+				if content != "" {
+					content += "\n"
+				}
+				content += fmt.Sprintf("[attachment: %s]", attachment.URL)
+			}
+		} else {
+			mediaPaths = append(mediaPaths, attachment.URL)
+			if content != "" {
+				content += "\n"
+			}
+			content += fmt.Sprintf("[attachment: %s]", attachment.URL)
 		}
-		content += fmt.Sprintf("[attachment: %s]", attachment.URL)
 	}

 	if content == "" && len(mediaPaths) == 0 {
@@ -136,3 +187,60 @@ func (c *DiscordChannel) handleMessage(s *discordgo.Session, m *discordgo.Messag

 	c.HandleMessage(senderID, m.ChannelID, content, mediaPaths, metadata)
 }
+
+func isAudioFile(filename, contentType string) bool {
+	audioExtensions := []string{".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma"}
+	audioTypes := []string{"audio/", "application/ogg", "application/x-ogg"}
+
+	for _, ext := range audioExtensions {
+		if strings.HasSuffix(strings.ToLower(filename), ext) {
+			return true
+		}
+	}
+
+	for _, audioType := range audioTypes {
+		if strings.HasPrefix(strings.ToLower(contentType), audioType) {
+			return true
+		}
+	}
+
+	return false
+}
+
+func (c *DiscordChannel) downloadAttachment(url, filename string) string {
+	mediaDir := filepath.Join(os.TempDir(), "picoclaw_media")
+	if err := os.MkdirAll(mediaDir, 0755); err != nil {
+		log.Printf("Failed to create media directory: %v", err)
+		return ""
+	}
+
+	localPath := filepath.Join(mediaDir, filename)
+
+	resp, err := http.Get(url)
+	if err != nil {
+		log.Printf("Failed to download attachment: %v", err)
+		return ""
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		log.Printf("Failed to download attachment, status: %d", resp.StatusCode)
+		return ""
+	}
+
+	out, err := os.Create(localPath)
+	if err != nil {
+		log.Printf("Failed to create file: %v", err)
+		return ""
+	}
+	defer out.Close()
+
+	_, err = io.Copy(out, resp.Body)
+	if err != nil {
+		log.Printf("Failed to write file: %v", err)
+		return ""
+	}
+
+	log.Printf("Attachment downloaded successfully to: %s", localPath)
+	return localPath
+}
--- a/pkg/channels/telegram.go
+++ b/pkg/channels/telegram.go
@@ -3,7 +3,11 @@ package channels
 import (
 	"context"
 	"fmt"
+	"io"
 	"log"
+	"net/http"
+	"os"
+	"path/filepath"
 	"regexp"
 	"strings"
 	"sync"
@@ -305,9 +309,20 @@ func (c *TelegramChannel) downloadFileWithInfo(file *tgbotapi.File, ext string)
 	url := file.Link(c.bot.Token)
 	log.Printf("File URL: %s", url)

-	mediaDir := "/tmp/picoclaw_media"
+	mediaDir := filepath.Join(os.TempDir(), "picoclaw_media")
+	if err := os.MkdirAll(mediaDir, 0755); err != nil {
+		log.Printf("Failed to create media directory: %v", err)
+		return ""
+	}

-	return fmt.Sprintf("%s/%s%s", mediaDir, file.FilePath[:min(16, len(file.FilePath))], ext)
+	localPath := filepath.Join(mediaDir, file.FilePath[:min(16, len(file.FilePath))]+ext)
+
+	if err := c.downloadFromURL(url, localPath); err != nil {
+		log.Printf("Failed to download file: %v", err)
+		return ""
+	}
+
+	return localPath
 }

 func min(a, b int) int {
@@ -317,6 +332,32 @@ func min(a, b int) int {
 	return b
 }

+func (c *TelegramChannel) downloadFromURL(url, localPath string) error {
+	resp, err := http.Get(url)
+	if err != nil {
+		return fmt.Errorf("failed to download: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("download failed with status: %d", resp.StatusCode)
+	}
+
+	out, err := os.Create(localPath)
+	if err != nil {
+		return fmt.Errorf("failed to create file: %w", err)
+	}
+	defer out.Close()
+
+	_, err = io.Copy(out, resp.Body)
+	if err != nil {
+		return fmt.Errorf("failed to write file: %w", err)
+	}
+
+	log.Printf("File downloaded successfully to: %s", localPath)
+	return nil
+}
+
 func (c *TelegramChannel) downloadFile(fileID, ext string) string {
 	file, err := c.bot.GetFile(tgbotapi.FileConfig{FileID: fileID})
 	if err != nil {
@@ -331,9 +372,20 @@ func (c *TelegramChannel) downloadFile(fileID, ext string) string {
 	url := file.Link(c.bot.Token)
 	log.Printf("File URL: %s", url)

-	mediaDir := "/tmp/picoclaw_media"
+	mediaDir := filepath.Join(os.TempDir(), "picoclaw_media")
+	if err := os.MkdirAll(mediaDir, 0755); err != nil {
+		log.Printf("Failed to create media directory: %v", err)
+		return ""
+	}

-	return fmt.Sprintf("%s/%s%s", mediaDir, fileID[:16], ext)
+	localPath := filepath.Join(mediaDir, fileID[:16]+ext)
+
+	if err := c.downloadFromURL(url, localPath); err != nil {
+		log.Printf("Failed to download file: %v", err)
+		return ""
+	}
+
+	return localPath
 }

 func parseChatID(chatIDStr string) (int64, error) {
--- a/pkg/voice/transcriber.go
+++ b/pkg/voice/transcriber.go
@@ -6,12 +6,13 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
-	"log"
 	"mime/multipart"
 	"net/http"
 	"os"
 	"path/filepath"
 	"time"
+
+	"github.com/sipeed/picoclaw/pkg/logger"
 )

 type GroqTranscriber struct {
@@ -27,6 +28,8 @@ type TranscriptionResponse struct {
 }

 func NewGroqTranscriber(apiKey string) *GroqTranscriber {
+	logger.DebugCF("voice", "Creating Groq transcriber", map[string]interface{}{"has_api_key": apiKey != ""})
+
 	apiBase := "https://api.groq.com/openai/v1"
 	return &GroqTranscriber{
 		apiKey:  apiKey,
@@ -38,79 +41,125 @@ func NewGroqTranscriber(apiKey string) *GroqTranscriber {
 }

 func (t *GroqTranscriber) Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error) {
-	log.Printf("Starting transcription for audio file: %s", audioFilePath)
+	logger.InfoCF("voice", "Starting transcription", map[string]interface{}{"audio_file": audioFilePath})

 	audioFile, err := os.Open(audioFilePath)
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to open audio file", map[string]interface{}{"path": audioFilePath, "error": err})
 		return nil, fmt.Errorf("failed to open audio file: %w", err)
 	}
 	defer audioFile.Close()

 	fileInfo, err := audioFile.Stat()
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to get file info", map[string]interface{}{"path": audioFilePath, "error": err})
 		return nil, fmt.Errorf("failed to get file info: %w", err)
 	}

+	logger.DebugCF("voice", "Audio file details", map[string]interface{}{
+		"size_bytes": fileInfo.Size(),
+		"file_name":  filepath.Base(audioFilePath),
+	})
+
 	var requestBody bytes.Buffer
 	writer := multipart.NewWriter(&requestBody)

 	part, err := writer.CreateFormFile("file", filepath.Base(audioFilePath))
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to create form file", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to create form file: %w", err)
 	}

-	if _, err := io.Copy(part, audioFile); err != nil {
+	copied, err := io.Copy(part, audioFile)
+	if err != nil {
+		logger.ErrorCF("voice", "Failed to copy file content", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to copy file content: %w", err)
 	}

+	logger.DebugCF("voice", "File copied to request", map[string]interface{}{"bytes_copied": copied})
+
 	if err := writer.WriteField("model", "whisper-large-v3"); err != nil {
+		logger.ErrorCF("voice", "Failed to write model field", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to write model field: %w", err)
 	}

 	if err := writer.WriteField("response_format", "json"); err != nil {
+		logger.ErrorCF("voice", "Failed to write response_format field", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to write response_format field: %w", err)
 	}

 	if err := writer.Close(); err != nil {
+		logger.ErrorCF("voice", "Failed to close multipart writer", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to close multipart writer: %w", err)
 	}

 	url := t.apiBase + "/audio/transcriptions"
 	req, err := http.NewRequestWithContext(ctx, "POST", url, &requestBody)
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to create request", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to create request: %w", err)
 	}

 	req.Header.Set("Content-Type", writer.FormDataContentType())
 	req.Header.Set("Authorization", "Bearer "+t.apiKey)

-	log.Printf("Sending transcription request to Groq API (file size: %d bytes)", fileInfo.Size())
+	logger.DebugCF("voice", "Sending transcription request to Groq API", map[string]interface{}{
+		"url":                url,
+		"request_size_bytes": requestBody.Len(),
+		"file_size_bytes":    fileInfo.Size(),
+	})

 	resp, err := t.httpClient.Do(req)
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to send request", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to send request: %w", err)
 	}
 	defer resp.Body.Close()

 	body, err := io.ReadAll(resp.Body)
 	if err != nil {
+		logger.ErrorCF("voice", "Failed to read response", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to read response: %w", err)
 	}

 	if resp.StatusCode != http.StatusOK {
+		logger.ErrorCF("voice", "API error", map[string]interface{}{
+			"status_code": resp.StatusCode,
+			"response":    string(body),
+		})
 		return nil, fmt.Errorf("API error (status %d): %s", resp.StatusCode, string(body))
 	}

+	logger.DebugCF("voice", "Received response from Groq API", map[string]interface{}{
+		"status_code":         resp.StatusCode,
+		"response_size_bytes": len(body),
+	})
+
 	var result TranscriptionResponse
 	if err := json.Unmarshal(body, &result); err != nil {
+		logger.ErrorCF("voice", "Failed to unmarshal response", map[string]interface{}{"error": err})
 		return nil, fmt.Errorf("failed to unmarshal response: %w", err)
 	}

-	log.Printf("Transcription completed successfully (text length: %d chars)", len(result.Text))
+	logger.InfoCF("voice", "Transcription completed successfully", map[string]interface{}{
+		"text_length":           len(result.Text),
+		"language":              result.Language,
+		"duration_seconds":      result.Duration,
+		"transcription_preview": truncateText(result.Text, 50),
+	})

 	return &result, nil
 }

 func (t *GroqTranscriber) IsAvailable() bool {
-	return t.apiKey != ""
+	available := t.apiKey != ""
+	logger.DebugCF("voice", "Checking transcriber availability", map[string]interface{}{"available": available})
+	return available
+}
+
+func truncateText(text string, maxLen int) string {
+	if len(text) <= maxLen {
+		return text
+	}
+	return text[:maxLen] + "..."
 }