diff --git a/pkg/asr/asr.go b/pkg/asr/asr.go index 2d2a87235..7b43f317f 100644 --- a/pkg/asr/asr.go +++ b/pkg/asr/asr.go @@ -1,21 +1,11 @@ package asr import ( - "bytes" "context" - "encoding/json" - "fmt" - "io" - "mime/multipart" - "net/http" - "os" - "path/filepath" "strings" - "time" "github.com/sipeed/picoclaw/pkg/config" - "github.com/sipeed/picoclaw/pkg/logger" - "github.com/sipeed/picoclaw/pkg/utils" + "github.com/sipeed/picoclaw/pkg/providers" ) type Transcriber interface { @@ -23,179 +13,34 @@ type Transcriber interface { Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error) } -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]any{"has_api_key": apiKey != ""}) +func supportsAudioTranscription(model string) bool { + protocol, _ := providers.ExtractProtocol(model) - apiBase := "https://api.groq.com/openai/v1" - return &GroqTranscriber{ - apiKey: apiKey, - apiBase: apiBase, - httpClient: &http.Client{ - Timeout: 60 * time.Second, - }, + switch protocol { + case "openai", "azure", "azure-openai", + "litellm", "openrouter", "groq", "zhipu", "gemini", "nvidia", + "ollama", "moonshot", "shengsuanyun", "deepseek", "cerebras", + "vivgrid", "volcengine", "vllm", "qwen", "qwen-intl", "qwen-international", "dashscope-intl", + "qwen-us", "dashscope-us", "mistral", "avian", "minimax", "longcat", "modelscope", "novita", + "coding-plan", "alibaba-coding", "qwen-coding": + // These protocols all go through the OpenAI-compatible or Azure provider path in + // providers.CreateProviderFromConfig, so they are the only ones that can supply + // the audio media payload shape expected by NewAudioModelTranscriber. + + // TODO: Further restrict this by modelID, since not every model under these + // protocols supports audio transcription. + return true + default: + return false } } -func (t *GroqTranscriber) TranscribeData( - ctx context.Context, - data []byte, - filename string, -) (*TranscriptionResponse, error) { - logger.InfoCF("voice", "Starting memory transcription", map[string]any{"filename": filename, "bytes": len(data)}) - - var requestBody bytes.Buffer - writer := multipart.NewWriter(&requestBody) - - part, err := writer.CreateFormFile("file", filename) - if err != nil { - logger.ErrorCF("voice", "Failed to create form file", map[string]any{"error": err}) - return nil, fmt.Errorf("failed to create form file: %w", err) - } - - if _, copyErr := io.Copy(part, bytes.NewReader(data)); copyErr != nil { - logger.ErrorCF("voice", "Failed to copy file content", map[string]any{"error": copyErr}) - return nil, fmt.Errorf("failed to copy file content: %w", copyErr) - } - - if err = writer.WriteField("model", "whisper-large-v3-turbo"); err != nil { - logger.ErrorCF("voice", "Failed to write model field", map[string]any{"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]any{"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]any{"error": err}) - return nil, fmt.Errorf("failed to close multipart writer: %w", err) - } - - return t.doRequest(ctx, &requestBody, writer.FormDataContentType(), int64(len(data))) -} - -func (t *GroqTranscriber) Transcribe(ctx context.Context, audioFilePath string) (*TranscriptionResponse, error) { - logger.InfoCF("voice", "Starting transcription", map[string]any{"audio_file": audioFilePath}) - - audioFile, err := os.Open(audioFilePath) - if err != nil { - return nil, fmt.Errorf("failed to open audio file %s: %w", audioFilePath, err) - } - defer audioFile.Close() - - fileInfo, err := audioFile.Stat() - if err != nil { - return nil, fmt.Errorf("failed to stat audio file %s: %w", audioFilePath, err) - } - - var requestBody bytes.Buffer - writer := multipart.NewWriter(&requestBody) - - part, err := writer.CreateFormFile("file", filepath.Base(audioFilePath)) - if err != nil { - return nil, fmt.Errorf("failed to create form file: %w", err) - } - - if _, copyErr := io.Copy(part, audioFile); copyErr != nil { - return nil, fmt.Errorf("failed to copy audio data: %w", copyErr) - } - - if err = writer.WriteField("model", "whisper-large-v3-turbo"); err != nil { - return nil, fmt.Errorf("failed to write model field: %w", err) - } - - if err = writer.WriteField("response_format", "json"); err != nil { - return nil, fmt.Errorf("failed to write response_format field: %w", err) - } - - if err = writer.Close(); err != nil { - return nil, fmt.Errorf("failed to close multipart writer: %w", err) - } - - return t.doRequest(ctx, &requestBody, writer.FormDataContentType(), fileInfo.Size()) -} - -func (t *GroqTranscriber) doRequest( - ctx context.Context, - requestBody *bytes.Buffer, - contentType string, - fileSize int64, -) (*TranscriptionResponse, error) { - 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]any{"error": err}) - return nil, fmt.Errorf("failed to create request: %w", err) - } - - req.Header.Set("Content-Type", contentType) - req.Header.Set("Authorization", "Bearer "+t.apiKey) - - logger.DebugCF("voice", "Sending transcription request to Groq API", map[string]any{ - "url": url, - "request_size_bytes": requestBody.Len(), - "file_size_bytes": fileSize, - }) - - resp, err := t.httpClient.Do(req) - if err != nil { - logger.ErrorCF("voice", "Failed to send request", map[string]any{"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]any{"error": err}) - return nil, fmt.Errorf("failed to read response: %w", err) - } - - if resp.StatusCode != http.StatusOK { - logger.ErrorCF("voice", "API error", map[string]any{ - "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]any{ - "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]any{"error": err}) - return nil, fmt.Errorf("failed to unmarshal response: %w", err) - } - - logger.InfoCF("voice", "Transcription completed successfully", map[string]any{ - "text_length": len(result.Text), - "language": result.Language, - "duration_seconds": result.Duration, - "transcription_preview": utils.Truncate(result.Text, 50), - }) - - return &result, nil -} - -func (t *GroqTranscriber) Name() string { - return "groq" -} - // DetectTranscriber inspects cfg and returns the appropriate Transcriber, or // nil if no supported transcription provider is configured. func DetectTranscriber(cfg *config.Config) Transcriber { @@ -208,6 +53,11 @@ func DetectTranscriber(cfg *config.Config) Transcriber { return NewAudioModelTranscriber(modelCfg) } } + + // Direct Groq provider config takes priority. + if key := cfg.Providers.Groq.APIKey; key != "" { + return NewGroqTranscriber(key) + } // Fall back to any model-list entry that uses the groq/ protocol or is explicitly named groq. for _, mc := range cfg.ModelList { if (strings.HasPrefix(mc.Model, "groq/") || mc.ModelName == "groq" || mc.Model == "whisper-large-v3-turbo") &&