diff --git a/TRANSCRIPTION_TOOL.md b/TRANSCRIPTION_TOOL.md
index 2570beed..c17ebe6a 100644
--- a/TRANSCRIPTION_TOOL.md
+++ b/TRANSCRIPTION_TOOL.md
@@ -1,7 +1,7 @@
# Meeting Assistant (Transcription Tool)
-**Version:** 0.5.0
-**Status:** Beta (Full Content Management)
+**Version:** 0.6.0
+**Status:** Beta (AI Insights Integration)
Der **Meeting Assistant** ist eine leistungsstarke Suite zur Transkription und Bearbeitung von Audio-Aufnahmen. Er kombiniert lokale FFmpeg-Verarbeitung mit der Gemini 2.0 Flash AI.
@@ -10,13 +10,19 @@ Der **Meeting Assistant** ist eine leistungsstarke Suite zur Transkription und B
## 1. Architektur & Stack
* **FFmpeg Engine:** Automatisches Splitting großer Dateien in 30-Minuten-Segmente.
-* **Gemini 2.0 Flash:** AI-Transkription mit Fokus auf JSON-Struktur (Sprecher, Timestamps).
-* **Structured Storage:** SQLite speichert jedes Segment als editierbares JSON-Array.
-* **Unified UI:** Das Frontend fügt alle Segmente zu einem nahtlosen Dokument zusammen.
+* **Gemini 2.0 Flash:** AI-Transkription mit Fokus auf JSON-Struktur (Sprecher, Timestamps) und zur Generierung von Meeting-Analysen.
+* **Prompt Library:** Eine Sammlung von Vorlagen zur Steuerung der KI-Analyse.
+* **Structured Storage:** SQLite speichert jedes Segment als editierbares JSON-Array und die Ergebnisse der KI-Analyse.
+* **Unified UI:** Das Frontend fügt alle Segmente zu einem nahtlosen Dokument zusammen und bietet interaktive Analyse-Funktionen.
---
-## 2. Key Features (v0.5.0)
+## 2. Key Features (v0.6.0)
+
+### 🚀 **NEU:** AI Insights auf Knopfdruck
+* **Meeting-Protokoll:** Erstellt automatisch ein formelles Protokoll (Meeting Minutes) mit Agenda, Entscheidungen und nächsten Schritten.
+* **Action Items:** Extrahiert eine Aufgabenliste mit Verantwortlichen und Fälligkeiten direkt aus dem Gespräch.
+* **Rollenbasierte Zusammenfassungen:** Generiert spezifische Zusammenfassungen, z.B. eine "Sales Summary", die sich auf Kundenbedürfnisse, Kaufsignale und nächste Schritte für das Vertriebsteam konzentriert.
### 🎙️ Intelligente Transkription
* Unterstützt MP3/WAV bis 500MB.
@@ -34,6 +40,7 @@ Der **Meeting Assistant** ist eine leistungsstarke Suite zur Transkription und B
### 📝 Editor & Export
* **Inline-Edit:** Jeder Textblock und jeder Sprechername kann durch direktes Anklicken korrigiert werden.
* **Copy Full Transcript:** Kopiert das gesamte, bereinigte Transkript inkl. Timestamps in die Zwischenablage.
+* **Copy Insights:** Jedes Analyse-Ergebnis kann einfach in die Zwischenablage kopiert werden.
---
@@ -43,7 +50,8 @@ Der **Meeting Assistant** ist eine leistungsstarke Suite zur Transkription und B
| :--- | :--- | :--- |
| `GET` | `/meetings` | Liste aller Meetings. |
| `POST` | `/upload` | Audio-Upload & Prozess-Start. |
-| `POST` | `.../rename_speaker` | **Neu:** Globale Umbenennung in der DB. |
+| `POST` | `/meetings/{id}/insights` | **Neu:** Generiert eine Analyse (z.B. Protokoll, Action Items). |
+| `POST` | `/meetings/{id}/rename_speaker` | Globale Umbenennung in der DB. |
| `PUT` | `/chunks/{id}` | Speichert manuelle Text-Korrekturen. |
| `DELETE` | `/meetings/{id}` | Vollständiges Löschen. |
@@ -51,5 +59,6 @@ Der **Meeting Assistant** ist eine leistungsstarke Suite zur Transkription und B
## 4. Roadmap
-* **v0.6: AI Insights:** Extraktion von Aufgaben (Action Items) und Zusammenfassungen per Button.
* **v0.7: Search:** Globale Suche über alle Transkripte hinweg.
+* **v0.8: Q&A an das Meeting:** Ermöglicht, Fragen direkt an das Transkript zu stellen ("Was wurde zu Thema X beschlossen?").
+* **v0.9: Export-Formate:** Export der Ergebnisse in verschiedene Formate (z.B. PDF, DOCX).
diff --git a/transcription-tool/backend/app.py b/transcription-tool/backend/app.py
index 5fd85dd0..dd462d3d 100644
--- a/transcription-tool/backend/app.py
+++ b/transcription-tool/backend/app.py
@@ -11,6 +11,7 @@ from datetime import datetime
from .config import settings
from .database import init_db, get_db, Meeting, TranscriptChunk, AnalysisResult, SessionLocal
from .services.orchestrator import process_meeting_task
+from .services.insights_service import generate_insight
# Initialize FastAPI App
app = FastAPI(
@@ -42,7 +43,8 @@ def list_meetings(db: Session = Depends(get_db)):
@app.get("/api/meetings/{meeting_id}")
def get_meeting(meeting_id: int, db: Session = Depends(get_db)):
meeting = db.query(Meeting).options(
- joinedload(Meeting.chunks)
+ joinedload(Meeting.chunks),
+ joinedload(Meeting.analysis_results) # Eager load analysis results
).filter(Meeting.id == meeting_id).first()
if not meeting:
@@ -99,6 +101,26 @@ async def upload_audio(
from pydantic import BaseModel
+class InsightRequest(BaseModel):
+ insight_type: str
+
+@app.post("/api/meetings/{meeting_id}/insights")
+def create_insight(meeting_id: int, payload: InsightRequest, db: Session = Depends(get_db)):
+ """
+ Triggers the generation of a specific insight (e.g., meeting minutes, action items).
+ If the insight already exists, it returns the stored result.
+ Otherwise, it generates, stores, and returns the new insight.
+ """
+ try:
+ insight = generate_insight(db, meeting_id, payload.insight_type)
+ return insight
+ except ValueError as e:
+ raise HTTPException(status_code=400, detail=str(e))
+ except Exception as e:
+ # For unexpected errors, return a generic 500 error
+ print(f"ERROR: Unexpected error in create_insight: {e}")
+ raise HTTPException(status_code=500, detail="An internal error occurred while generating the insight.")
+
class RenameRequest(BaseModel):
old_name: str
new_name: str
diff --git a/transcription-tool/backend/prompt_library.py b/transcription-tool/backend/prompt_library.py
new file mode 100644
index 00000000..41afc8c3
--- /dev/null
+++ b/transcription-tool/backend/prompt_library.py
@@ -0,0 +1,113 @@
+
+MEETING_MINUTES_PROMPT = """
+You are a professional assistant specialized in summarizing meeting transcripts.
+Your task is to create a formal and structured protocol (Meeting Minutes) from the provided transcript.
+
+Please analyze the following transcript and generate the Meeting Minutes in German.
+
+**Transcript:**
+---
+{transcript_text}
+---
+
+**Instructions for the Meeting Minutes:**
+
+1. **Header:**
+ * Start with a clear title: "Meeting-Protokoll".
+ * Add a placeholder for the meeting date: "Datum: [Datum des Meetings]".
+
+2. **Agenda Items:**
+ * Identify the main topics discussed.
+ * Structure the protocol using these topics as headlines (e.g., "Tagesordnungspunkt 1: [Thema]").
+
+3. **Key Discussions & Decisions:**
+ * For each agenda item, summarize the key points of the discussion.
+ * Clearly list all decisions that were made. Use a format like "**Entscheidung:** ...".
+
+4. **Action Items (Next Steps):**
+ * Extract all clear tasks or action items.
+ * For each action item, identify the responsible person (Owner) and the deadline, if mentioned.
+ * Present the action items in a clear list under a headline "Nächste Schritte / Action Items". Use the format: "- [Aufgabe] (Verantwortlich: [Person], Fällig bis: [Datum/unbestimmt])".
+
+5. **General Tone & Language:**
+ * The protocol must be written in formal, professional German.
+ * Be concise and focus on the essential information (discussions, decisions, tasks).
+ * Do not invent information that is not present in the transcript.
+
+Please provide the output in Markdown format.
+"""
+
+ACTION_ITEMS_PROMPT = """
+You are a highly efficient assistant focused on productivity and task management.
+Your goal is to extract all actionable tasks (Action Items) from a meeting transcript.
+
+Please analyze the following transcript and list all tasks.
+
+**Transcript:**
+---
+{transcript_text}
+---
+
+**Instructions for the Action Item List:**
+
+1. **Extraction:**
+ * Carefully read the entire transcript and identify every statement that constitutes a task, a to-do, or a commitment to do something.
+ * Ignore general discussions, opinions, and status updates. Focus only on future actions.
+
+2. **Format:**
+ * Present the extracted tasks as a bulleted list.
+ * For each task, clearly state:
+ * **What** needs to be done.
+ * **Who** is responsible for it (Owner).
+ * **When** it should be completed by (Due Date), if mentioned.
+
+3. **Output Structure:**
+ * Use the following format for each item: `- [Task Description] (Owner: [Person's Name], Due: [Date/unspecified])`
+ * If the owner or due date is not explicitly mentioned, use "[unbestimmt]".
+ * The list should be titled "Action Item Liste".
+
+4. **Language:**
+ * The output should be in German.
+
+Please provide the output in Markdown format.
+"""
+
+SALES_SUMMARY_PROMPT = """
+You are a Senior Sales Manager analyzing a meeting transcript from a client conversation.
+Your objective is to create a concise, rollenbasierte Zusammenfassung for the sales team. The summary should highlight key information relevant to closing a deal.
+
+Please analyze the following transcript and generate a Sales Summary.
+
+**Transcript:**
+---
+{transcript_text}
+---
+
+**Instructions for the Sales Summary:**
+
+1. **Customer Needs & Pain Points:**
+ * Identify and list the core problems, challenges, and needs expressed by the client.
+ * What are their primary business goals?
+
+2. **Buying Signals:**
+ * Extract any phrases or questions that indicate a strong interest in the product/service (e.g., questions about price, implementation, specific features).
+
+3. **Key Decision-Makers:**
+ * Identify the people in the meeting who seem to have the most influence on the purchasing decision. Note their role or title if mentioned.
+
+4. **Budget & Timeline:**
+ * Note any mentions of budget, pricing expectations, or the timeline for their decision-making process.
+
+5. **Next Steps (from a Sales Perspective):**
+ * What are the immediate next actions the sales team needs to take to move this deal forward? (e.g., "Send proposal," "Schedule demo for the technical team").
+
+**Output Format:**
+* Use clear headings for each section (e.g., "Kundenbedürfnisse & Pain Points", "Kaufsignale").
+* Use bullet points for lists.
+* The language should be direct, actionable, and in German.
+
+Please provide the output in Markdown format.
+"""
+
+# You can add more prompts here for other analysis types.
+# For example, a prompt for a technical summary, a marketing summary, etc.
diff --git a/transcription-tool/backend/services/insights_service.py b/transcription-tool/backend/services/insights_service.py
new file mode 100644
index 00000000..621232c7
--- /dev/null
+++ b/transcription-tool/backend/services/insights_service.py
@@ -0,0 +1,110 @@
+import sys
+import os
+from sqlalchemy.orm import Session
+from .. import database
+from .. import prompt_library
+
+# Add project root to path to allow importing from 'helpers'
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..', '..')))
+from helpers import call_gemini_flash
+
+def _format_transcript(chunks: list[database.TranscriptChunk]) -> str:
+ """
+ Formats the transcript chunks into a single, human-readable string.
+ Example: "[00:00:01] Speaker A: Hello world."
+ """
+ full_transcript = []
+ # Sort chunks by their index to ensure correct order
+ sorted_chunks = sorted(chunks, key=lambda c: c.chunk_index)
+
+ for chunk in sorted_chunks:
+ if not chunk.json_content:
+ continue
+
+ for item in chunk.json_content:
+ # json_content can be a list of dicts
+ if isinstance(item, dict):
+ speaker = item.get('speaker', 'Unknown')
+ start_time = item.get('start', 0)
+ text = item.get('line', '')
+
+ # Format timestamp from seconds to HH:MM:SS
+ hours, remainder = divmod(int(start_time), 3600)
+ minutes, seconds = divmod(remainder, 60)
+ timestamp = f"{hours:02}:{minutes:02}:{seconds:02}"
+
+ full_transcript.append(f"[{timestamp}] {speaker}: {text}")
+
+ return "\n".join(full_transcript)
+
+def get_prompt_by_type(insight_type: str) -> str:
+ """
+ Returns the corresponding prompt from the prompt_library based on the type.
+ """
+ if insight_type == "meeting_minutes":
+ return prompt_library.MEETING_MINUTES_PROMPT
+ elif insight_type == "action_items":
+ return prompt_library.ACTION_ITEMS_PROMPT
+ elif insight_type == "sales_summary":
+ return prompt_library.SALES_SUMMARY_PROMPT
+ else:
+ raise ValueError(f"Unknown insight type: {insight_type}")
+
+def generate_insight(db: Session, meeting_id: int, insight_type: str) -> database.AnalysisResult:
+ """
+ Generates a specific insight for a meeting, stores it, and returns it.
+ Checks for existing analysis to avoid re-generating.
+ """
+ # 1. Check if the insight already exists
+ existing_insight = db.query(database.AnalysisResult).filter(
+ database.AnalysisResult.meeting_id == meeting_id,
+ database.AnalysisResult.prompt_key == insight_type
+ ).first()
+
+ if existing_insight:
+ return existing_insight
+
+ # 2. Get the meeting and its transcript
+ meeting = db.query(database.Meeting).filter(database.Meeting.id == meeting_id).first()
+ if not meeting:
+ raise ValueError(f"Meeting with id {meeting_id} not found.")
+
+ if not meeting.chunks:
+ raise ValueError(f"Meeting with id {meeting_id} has no transcript chunks.")
+
+ # 3. Format the transcript and select the prompt
+ transcript_text = _format_transcript(meeting.chunks)
+ if not transcript_text.strip():
+ raise ValueError(f"Transcript for meeting {meeting_id} is empty.")
+
+ prompt_template = get_prompt_by_type(insight_type)
+ final_prompt = prompt_template.format(transcript_text=transcript_text)
+
+ # 4. Call the AI model
+ # Update meeting status
+ meeting.status = "ANALYZING"
+ db.commit()
+
+ try:
+ generated_text = call_gemini_flash(prompt=final_prompt, temperature=0.5)
+
+ # 5. Store the new insight
+ new_insight = database.AnalysisResult(
+ meeting_id=meeting_id,
+ prompt_key=insight_type,
+ result_text=generated_text
+ )
+ db.add(new_insight)
+
+ meeting.status = "COMPLETED"
+ db.commit()
+ db.refresh(new_insight)
+
+ return new_insight
+
+ except Exception as e:
+ meeting.status = "ERROR"
+ db.commit()
+ # Log the error properly in a real application
+ print(f"Error generating insight for meeting {meeting_id}: {e}")
+ raise
diff --git a/transcription-tool/frontend/src/App.tsx b/transcription-tool/frontend/src/App.tsx
index ac893a76..b77cd571 100644
--- a/transcription-tool/frontend/src/App.tsx
+++ b/transcription-tool/frontend/src/App.tsx
@@ -1,10 +1,19 @@
import React, { useState, useEffect } from 'react'
import axios from 'axios'
-import { Upload, FileText, Clock, CheckCircle2, Loader2, AlertCircle, Trash2, ArrowLeft, Copy, Edit3, X, Scissors, Users } from 'lucide-react'
+import { Upload, FileText, Clock, CheckCircle2, Loader2, AlertCircle, Trash2, ArrowLeft, Copy, Edit3, X, Scissors, Users, Wand2 } from 'lucide-react'
import clsx from 'clsx'
const API_BASE = '/tr/api'
+// --- INTERFACES ---
+
+interface AnalysisResult {
+ id: number;
+ prompt_key: string;
+ result_text: string;
+ created_at: string;
+}
+
interface TranscriptMessage {
time: string
display_time: string
@@ -30,8 +39,29 @@ interface Meeting {
duration_seconds?: number
created_at: string
chunks?: Chunk[]
+ analysis_results?: AnalysisResult[]
}
+// --- MODAL COMPONENT ---
+
+const InsightModal = ({ title, content, onClose, onCopy }: { title: string, content: string, onClose: () => void, onCopy: (text: string) => void }) => (
+
+
+
+
{title}
+
+
+
+
+
+
+
{content}
+
+
+
+)
+
+
export default function App() {
const [view, setView] = useState<'list' | 'detail'>('list')
const [selectedId, setSelectedId] = useState(null)
@@ -48,6 +78,12 @@ export default function App() {
const [editValue, setEditValue] = useState("")
const [isProcessing, setIsProcessing] = useState(false)
+ // Insight State
+ const [showInsightModal, setShowInsightModal] = useState(false)
+ const [insightLoading, setInsightLoading] = useState(false)
+ const [insightResult, setInsightResult] = useState('')
+ const [insightTitle, setInsightTitle] = useState('')
+
const fetchMeetings = async () => {
try {
const res = await axios.get(`${API_BASE}/meetings`)
@@ -102,6 +138,39 @@ export default function App() {
} catch (e) { alert("Delete failed") }
}
+ // --- AI INSIGHTS ---
+
+ const handleGenerateInsight = async (insightType: string, title: string) => {
+ if (!detailMeeting) return;
+ setInsightLoading(true);
+ setInsightTitle(title);
+
+ try {
+ // First, check if result already exists
+ const existing = detailMeeting.analysis_results?.find(r => r.prompt_key === insightType);
+ if (existing) {
+ setInsightResult(existing.result_text);
+ setShowInsightModal(true);
+ return;
+ }
+
+ // If not, generate it
+ const res = await axios.post(`${API_BASE}/meetings/${detailMeeting.id}/insights`, {
+ insight_type: insightType
+ });
+ setInsightResult(res.data.result_text);
+ setShowInsightModal(true);
+ // Refresh detail view to get the new analysis result in the meeting object
+ fetchDetail(detailMeeting.id);
+ } catch(e) {
+ console.error("Failed to generate insight", e);
+ alert(`Error: Could not generate ${title}.`);
+ } finally {
+ setInsightLoading(false);
+ }
+ }
+
+
// --- GLOBAL SPEAKER MANAGEMENT ---
const getUniqueSpeakers = () => {
@@ -235,6 +304,7 @@ export default function App() {
return (