添加API服务模块

api/services/__init__.py

@@ -0,0 +1,11 @@
+"""
+服务模块
+"""
+from .asr_service import asr_service
+from .tts_service import tts_service
+
+__all__ = [
+    "asr_service",
+    "tts_service",
+]
+

api/services/asr_service.py

@@ -0,0 +1,64 @@
+"""
+ASR 服务：语音转文字
+"""
+import os
+import base64
+from typing import Optional, Any, Coroutine
+from openai import OpenAI
+
+
+class ASRService:
+    """ASR 服务（语音转文字）"""
+    
+    def __init__(self):
+        api_key = os.getenv("OPENAI_API_KEY", "")
+        if api_key:
+            self.client = OpenAI(api_key=api_key)
+        else:
+            self.client = None
+    
+    async def transcribe(self, audio_base64: str) -> str | None:
+        """
+        转写音频为文字
+        
+        Args:
+            audio_base64: Base64 编码的音频数据
+        
+        Returns:
+            转写文本
+        """
+        if not self.client:
+            # 如果没有配置 API Key，返回模拟数据
+            return "这是模拟的转写文本（请配置 OPENAI_API_KEY 以使用实际 ASR 功能）"
+        
+        try:
+            # 解码 Base64 音频
+            audio_bytes = base64.b64decode(audio_base64)
+            
+            # 保存临时文件
+            import tempfile
+            with tempfile.NamedTemporaryFile(suffix=".m4a", delete=False) as tmp_file:
+                tmp_file.write(audio_bytes)
+                tmp_file_path = tmp_file.name
+            
+            try:
+                # 调用 OpenAI Whisper API
+                with open(tmp_file_path, "rb") as audio_file:
+                    transcript = self.client.audio.transcriptions.create(
+                        model="whisper-1",
+                        file=audio_file,
+                        language="zh"  # 中文
+                    )
+                return transcript.text
+            finally:
+                # 清理临时文件
+                import os
+                if os.path.exists(tmp_file_path):
+                    os.remove(tmp_file_path)
+        except Exception as e:
+            # 出错时返回错误信息
+            return f"转写失败: {str(e)}"
+
+
+# 全局实例
+asr_service = ASRService()

api/services/pdf_service.py

@@ -0,0 +1,107 @@
+"""
+PDF 生成服务
+"""
+from typing import List
+from reportlab.lib.pagesizes import letter, A4
+from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
+from reportlab.lib.units import inch
+from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak
+from reportlab.pdfbase import pdfmetrics
+from reportlab.pdfbase.ttfonts import TTFont
+from reportlab.pdfbase.cidfonts import UnicodeCIDFont
+from io import BytesIO
+import os
+
+
+class PDFService:
+    """PDF 生成服务"""
+    
+    def __init__(self):
+        # 尝试注册中文字体
+        try:
+            # 使用系统字体或 ReportLab 内置的中文字体
+            # 如果没有中文字体文件，使用 UnicodeCIDFont
+            pdfmetrics.registerFont(UnicodeCIDFont('STSong-Light'))
+            self.chinese_font = 'STSong-Light'
+        except Exception:
+            # 如果注册失败，使用默认字体（可能不支持中文）
+            self.chinese_font = 'Helvetica'
+    
+    async def generate_pdf(self, book, chapters: List) -> bytes:
+        """
+        生成 PDF
+        
+        Args:
+            book: 回忆录对象
+            chapters: 章节列表
+        
+        Returns:
+            PDF 字节数据
+        """
+        buffer = BytesIO()
+        doc = SimpleDocTemplate(buffer, pagesize=A4)
+        
+        # 创建样式
+        styles = getSampleStyleSheet()
+        title_style = ParagraphStyle(
+            'CustomTitle',
+            parent=styles['Heading1'],
+            fontSize=24,
+            spaceAfter=30,
+            alignment=1,  # 居中
+            fontName=self.chinese_font
+        )
+        
+        heading_style = ParagraphStyle(
+            'CustomHeading',
+            parent=styles['Heading1'],
+            fontSize=18,
+            spaceAfter=12,
+            fontName=self.chinese_font
+        )
+        
+        normal_style = ParagraphStyle(
+            'CustomNormal',
+            parent=styles['Normal'],
+            fontSize=12,
+            leading=18,
+            fontName=self.chinese_font
+        )
+        
+        # 构建内容
+        story = []
+        
+        # 封面
+        story.append(Paragraph(book.title, title_style))
+        story.append(Spacer(1, 0.5*inch))
+        story.append(PageBreak())
+        
+        # 目录
+        story.append(Paragraph("目录", heading_style))
+        story.append(Spacer(1, 0.2*inch))
+        for i, chapter in enumerate(chapters, 1):
+            story.append(Paragraph(f"{i}. {chapter.title}", normal_style))
+        story.append(PageBreak())
+        
+        # 章节内容
+        for chapter in chapters:
+            story.append(Paragraph(chapter.title, heading_style))
+            story.append(Spacer(1, 0.2*inch))
+            
+            # 分段处理内容
+            paragraphs = chapter.content.split('\n\n')
+            for para in paragraphs:
+                if para.strip():
+                    story.append(Paragraph(para.strip(), normal_style))
+                    story.append(Spacer(1, 0.1*inch))
+            
+            story.append(PageBreak())
+        
+        # 生成 PDF
+        doc.build(story)
+        buffer.seek(0)
+        return buffer.read()
+
+
+# 全局实例
+pdf_service = PDFService()

api/services/tts_service.py

@@ -0,0 +1,59 @@
+"""
+TTS 服务：文字转语音
+"""
+import base64
+import os
+from io import BytesIO
+
+from openai import OpenAI
+
+
+class TTSService:
+    """TTS 服务（文字转语音）"""
+    
+    def __init__(self):
+        api_key = os.getenv("OPENAI_API_KEY", "")
+        if api_key:
+            self.client = OpenAI(api_key=api_key)
+        else:
+            self.client = None
+    
+    async def synthesize(self, text: str) -> str:
+        """
+        将文字转换为语音
+        
+        Args:
+            text: 要转换的文字
+        
+        Returns:
+            Base64 编码的音频数据
+        """
+        if not self.client:
+            # 如果没有配置 API Key，返回空字符串
+            return ""
+        
+        try:
+            # 调用 OpenAI TTS API
+            response = self.client.audio.speech.create(
+                model="tts-1",
+                voice="alloy",  # 可选: alloy, echo, fable, onyx, nova, shimmer
+                input=text
+            )
+            
+            # 读取音频数据
+            audio_bytes = BytesIO()
+            for chunk in response.iter_bytes():
+                audio_bytes.write(chunk)
+            
+            # 转换为 Base64
+            audio_data = audio_bytes.getvalue()
+            audio_base64 = base64.b64encode(audio_data).decode('utf-8')
+            return audio_base64
+        except Exception as e:
+            # 出错时返回空字符串
+            print(f"TTS 生成失败: {str(e)}")
+            return ""
+
+
+# 全局实例
+tts_service = TTSService()