Launched this week

OWEN Podcast Studio

Launched this week

Turn English podcasts into Chinese, locally

1 follower

Turn English podcasts into Chinese, locally

1 follower

Visit website

OWEN 中文播客节目库，支持移动端Turn English podcasts into Chinese audio on your Windows PC. OWEN Podcast Studio combines RSS import, transcription, speaker-aware translation, multi-voice narration, audio checks and mastering. Process episodes in batches, reuse completed work and publish to a mobile-friendly listening library. Developed with GPT-6 Astra; speech recognition, translation and narration run on local models.播放与断点续播。

Free

Launch tags:Languages•OpenAI Day

Launch Team / Built With

ClarifyThe autonomous CRM that helps you sell more

Promoted

OpenAI

GPT-6 Astra Challenge

How did Astra change the scope or ambition of what you built?

Maker

GPT-6 Astra changed this project from a collection of local podcast translation scripts into an end-to-end Windows production system. With Astra helping me reason across the whole workflow, I expanded the scope to cover RSS/local-audio intake, transcription, speaker-aware processing, context-aware translation, multi-voice narration, audio verification, mastering, resumable batch production, and mobile-friendly publishing. Astra was especially useful for tracing failures across stages, tightening recovery logic, and iterating on the GUI and product flow. The production pipeline itself still runs local models; Astra's role was in designing, implementing, debugging and refining the software. Without Astra, I would likely have stopped at a narrower translation/TTS tool instead of building a repeatable full-stack podcast localization workflow.

Report

1d ago

Maker

📌

Hi Product Hunt, I'm Owen, the maker of OWEN Podcast Studio. I built this to turn long-form English podcasts into Chinese audio, not just translated transcripts. The goal is a complete listening experience with clear speaker changes and natural pacing. The Windows app brings RSS import or local audio, transcription, speaker identification, context-aware translation, multi-voice narration, audio checks and mastering into one workflow. It supports batch processing and reuses completed stages, so fixing part of an episode does not have to mean starting over. Finished episodes can be published to a mobile-friendly library with search and playback resumption. The project builds on pyVideoTrans and local AI models. I used GPT-6 Astra to develop and iterate on the software. Speech recognition, translation and voice generation run locally, without requiring a cloud AI API for those steps. The linked website is a listening demo of the output, not a browser-based conversion service. The product behind it is the Windows production workflow. AI transcription and translation can still make mistakes, so the audio checks are safeguards rather than a promise of perfect output. I'd especially value feedback on translation fidelity, speaker continuity and listening comfort over a full episode. What would make this useful for your own listening or podcast localization workflow?

Report

7d ago