Earnings Call Processor
End-to-end pipeline: audio → transcript → stock analysis → Feishu document.
Workflow
- Transcribe — Run Whisper on earnings call audio (WAV/MP3/M4A)
- Analyze — Load CSV stock history, compute key financial indicators
- Generate — Build a structured Feishu document with transcript + financials
- Publish — Create as draft first, then promote to shared doc after review
Usage
python3 src/process_earnings_call.py \
--audio audio_transcripts/earnings_call_sample.wav \
--stock-csv financial_reports/aapl_stock_history.csv \
--symbol AAPL \
--output-dir /tmp/earnings_output
Feishu document creation
After the local output is ready, use the feishu-doc skill to publish:
python3 /path/to/feishu-doc/scripts/doc_ctl.py create "AAPL Earnings Call Summary" --content "$(cat /tmp/earnings_output/feishu_content.md)"
Requirements
whisper(OpenAI Whisper CLI)pandas- Python 3.10+
Output
{output_dir}/transcript.txt— Raw Whisper transcript{output_dir}/financial_indicators.json— Computed indicators{output_dir}/feishu_content.md— Structured content ready for Feishu doc