166 lines
5.3 KiB
Go
166 lines
5.3 KiB
Go
package voice
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"io"
|
|
"mime/multipart"
|
|
"net/http"
|
|
"os"
|
|
"path/filepath"
|
|
"time"
|
|
|
|
"github.com/sipeed/picoclaw/pkg/logger"
|
|
)
|
|
|
|
type GroqTranscriber struct {
|
|
apiKey string
|
|
apiBase string
|
|
httpClient *http.Client
|
|
}
|
|
|
|
type TranscriptionResponse struct {
|
|
Text string `json:"text"`
|
|
Language string `json:"language,omitempty"`
|
|
Duration float64 `json:"duration,omitempty"`
|
|
}
|
|
|
|
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,
|
|
apiBase: apiBase,
|
|
httpClient: &http.Client{
|
|
Timeout: 60 * time.Second,
|
|
},
|
|
}
|
|
}
|
|
|
|
func (t *GroqTranscriber) Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error) {
|
|
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)
|
|
}
|
|
|
|
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)
|
|
|
|
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)
|
|
}
|
|
|
|
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 {
|
|
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] + "..."
|
|
}
|