Update app.py

app.py

@@ -328,6 +328,73 @@ def create_file(prompt, response, file_type="md"):
         f.write(prompt + "\n\n" + response)
     return filename
 
+
+
+def get_download_link(file, file_type="zip"):
+    """
+    Convert a file to base64 and return an HTML link for download.
+    """
+    with open(file, "rb") as f:
+        b64 = base64.b64encode(f.read()).decode()
+    if file_type == "zip":
+        return f'<a href="data:application/zip;base64,{b64}" download="{os.path.basename(file)}">📂 Download {os.path.basename(file)}</a>'
+    elif file_type == "mp3":
+        return f'<a href="data:audio/mpeg;base64,{b64}" download="{os.path.basename(file)}">🎵 Download {os.path.basename(file)}</a>'
+    elif file_type == "wav":
+        return f'<a href="data:audio/wav;base64,{b64}" download="{os.path.basename(file)}">🔊 Download {os.path.basename(file)}</a>'
+    elif file_type == "md":
+        return f'<a href="data:text/markdown;base64,{b64}" download="{os.path.basename(file)}">📝 Download {os.path.basename(file)}</a>'
+    else:
+        return f'<a href="data:application/octet-stream;base64,{b64}" download="{os.path.basename(file)}">Download {os.path.basename(file)}</a>'
+
+def clean_for_speech(text: str) -> str:
+    """Clean up text for TTS output."""
+    text = text.replace("\n", " ")
+    text = text.replace("</s>", " ")
+    text = text.replace("#", "")
+    text = re.sub(r"\(https?:\/\/[^\)]+\)", "", text)
+    text = re.sub(r"\s+", " ", text).strip()
+    return text
+
+async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0, file_format="mp3"):
+    """Async TTS generation with edge-tts library."""
+    text = clean_for_speech(text)
+    if not text.strip():
+        return None
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
+    out_fn = generate_filename(text, text, file_type=file_format)
+    await communicate.save(out_fn)
+    return out_fn
+
+def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0, file_format="mp3"):
+    """Wrapper for the async TTS generate call."""
+    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch, file_format))
+
+def play_and_download_audio(file_path, file_type="mp3"):
+    """Streamlit audio + a quick download link."""
+    if file_path and os.path.exists(file_path):
+        st.audio(file_path)
+        dl_link = get_download_link(file_path, file_type=file_type)
+        st.markdown(dl_link, unsafe_allow_html=True)
+
+def save_qa_with_audio(question, answer, voice=None):
+    """Save Q&A to markdown and also generate audio."""
+    if not voice:
+        voice = st.session_state['tts_voice']
+    
+    combined_text = f"# Question\n{question}\n\n# Answer\n{answer}"
+    md_file = create_file(question, answer, "md")
+    audio_text = f"{question}\n\nAnswer: {answer}"
+    audio_file = speak_with_edge_tts(
+        audio_text,
+        voice=voice,
+        file_format=st.session_state['audio_format']
+    )
+    return md_file, audio_file
+
+    
 # ─────────────────────────────────────────────────────────
 # 4. OPTIMIZED AUDIO GENERATION (ASYNC TTS + CACHING)
 # ─────────────────────────────────────────────────────────