Generate a 2-speaker podcast from text input or documents!
Transcribe voice to text
Transcribe audio recordings into text
Transcribe audio to text using your microphone
Transcribe audio to text
Transcribe audio to text
Transcribe audio to text with speaker diarization
Transcribe audio into text
Transcribe audio to text
西北工业大学ASLP实验室OSUM项目demo展示
Generate podcast audio from text or documents
Transcribe audio to text
Transcribe audio in realtime - Gradio UI version
PodcastGen is an AI-powered tool designed to generate a 2-speaker podcast from text input or documents. It allows users to easily convert written content into a natural-sounding podcast, complete with AI-generated voices for both speakers. This innovative tool is perfect for content creators, podcasters, and anyone looking to repurpose written material into engaging audio content.
• Text-to-Podcast Conversion: Transform written content into a Podcast with AI-generated voices for two speakers.
• Document Support: Upload documents or paste text directly into the interface for conversion.
• Customizable Voices: Choose from a variety of voice options to match your desired tone and style.
• Audio Transcription: Generate high-quality audio files that mimic natural conversations.
• Multi-Speaker Support: Create podcasts with two distinct voices for a realistic dialogue experience.
• Seamless Integration: Easy-to-use interface for quick and efficient podcast generation.
What formats does PodcastGen support for input?
PodcastGen supports text input directly or document uploads in formats like PDF, Word, or TXT.
Can I customize the voices or tones of the speakers?
Yes, PodcastGen offers customizable voice options, allowing you to select voices and adjust tones to match your desired podcast style.
How long does it take to generate a podcast?
Generation time depends on the length of the input text, but PodcastGen typically produces high-quality audio quickly, even for longer documents.