Cld2labs/pdf podcast

[gopal-raj-suresh]

Description

This PR introduces the PdfToPodcast blueprint — a microservices-based GenAI application that converts PDF documents into engaging podcast-style audio conversations. The blueprint implements a multi-stage pipeline (PDF extraction → dialogue generation → audio synthesis) with full user control over script editing and voice selection.

Key Features:

• Multi-stage pipeline: PDF → Text → Dialogue → Audio
• OCR support for scanned documents
• LLM-powered conversational dialogue generation
• Multi-voice text-to-speech (TTS) generation
• Interactive script editing interface
• Real-time audio preview with waveform visualization
• Project management and history tracking

Issues

n/a

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds new functionality)
• Breaking change (fix or feature that would break existing design and interface)
• Others (enhancement, documentation, validation, etc.)

Dependencies

No new repository-level dependencies.

All dependencies for the PdfToPodcast blueprint are listed in:

• PDF Service: PdfToPodcast/api/pdf-service/requirements.txt
• LLM Service: PdfToPodcast/api/llm-service/requirements.txt
• TTS Service: PdfToPodcast/api/tts-service/requirements.txt
• Frontend: PdfToPodcast/ui/package.json

Key technologies: FastAPI microservices, React, Redux Toolkit, OCR, OpenAI-compatible LLM/TTS

Tests

Testing Instructions:

git clone https://github.com/cld2labs/GenAIExamples.git
cd GenAIExamples
git checkout cld2labs/pdf-podcast
cd PdfToPodcast

[github-actions]

Dependency Review

The following issues were found:

• ❌ 6 vulnerable package(s)
• ✅ 0 package(s) with incompatible licenses
• ✅ 0 package(s) with invalid SPDX license definitions
• ⚠️ 4 package(s) with unknown licenses.

See the Details below.

Vulnerabilities

PdfToPodcast/api/llm-service/requirements.txt

Name	Version	Vulnerability	Severity
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high
requests	2.31.0	Requests `Session` object does not verify requests after making first request with verify=False	moderate
		Requests vulnerable to .netrc credentials leak via malicious URLs	moderate

PdfToPodcast/api/pdf-service/requirements.txt

Name	Version	Vulnerability	Severity
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high
requests	2.31.0	Requests `Session` object does not verify requests after making first request with verify=False	moderate
		Requests vulnerable to .netrc credentials leak via malicious URLs	moderate
Pillow	10.1.0	Arbitrary Code Execution in Pillow	critical
		Pillow buffer overflow vulnerability	high
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high
PyPDF2	3.0.1	pypdf and PyPDF2 possible Infinite Loop when a comment isn't followed by a character	moderate

PdfToPodcast/requirements.txt

Name	Version	Vulnerability	Severity
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high
requests	2.31.0	Requests `Session` object does not verify requests after making first request with verify=False	moderate
		Requests vulnerable to .netrc credentials leak via malicious URLs	moderate
Pillow	10.1.0	Arbitrary Code Execution in Pillow	critical
		Pillow buffer overflow vulnerability	high
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high
PyPDF2	3.0.1	pypdf and PyPDF2 possible Infinite Loop when a comment isn't followed by a character	moderate
python-multipart	0.0.6	python-multipart vulnerable to Content-Type Header ReDoS	high
		Denial of service (DoS) via deformation `multipart/form-data` boundary	high

License Issues

PdfToPodcast/api/pdf-service/requirements.txt

Package	Version	License	Issue Type
Pillow	10.1.0	Null	Unknown License
PyPDF2	3.0.1	Null	Unknown License

PdfToPodcast/api/tts-service/requirements.txt

Package	Version	License	Issue Type
python-multipart	>= 0.0.12	Null	Unknown License

PdfToPodcast/ui/package.json

Package	Version	License	Issue Type
lucide-react	^0.294.0	Null	Unknown License

Scanned Files

• PdfToPodcast/api/llm-service/requirements.txt
• PdfToPodcast/api/pdf-service/requirements.txt
• PdfToPodcast/api/tts-service/requirements.txt
• PdfToPodcast/requirements.txt
• PdfToPodcast/ui/package.json