soul-ailab/soulx-podcast

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 1 hour ago
Added to GitGenius on September 19th, 2026
Created on September 22nd, 2025
Open Issues & Pull Requests: 49 (+0)
GitHub issues: Enabled
Number of forks: 456
Total Stargazers: 3,556 (+0)
Total Subscribers: 17 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 47.0 hours
Mean response time: 4.5 days
90th percentile: 12.7 days
Tracked items: 36

Most active contributors

Sign in to see contributor activity.

How this project is maintained

Roughly one issue in two opened in the past year never receives a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. 95% of tracked open issues have had no activity in three months, so the open count overstates what is actively being worked. Only 35% of issues opened in the past year have been closed. Three people close 74% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 40
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 268 days
Stale 30+ days: 40
Stale 90+ days: 38

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

SoulX-Podcast is an inference codebase for generating high-fidelity podcasts from text with support for multiple speakers, dialects, and paralinguistic features.

The tool addresses the challenge of creating realistic long-form podcast audio by combining multi-speaker dialogue generation with fine-grained control over speech characteristics. It handles multi-turn conversational scenarios where different speakers alternate, moving beyond traditional single-speaker text-to-speech synthesis. The system supports Mandarin and English as primary languages, along with several Chinese dialects including Sichuanese, Henanese, and Cantonese. Users can inject paralinguistic events such as laughter, sighs, breathing, coughing, and throat clearing through special tags to enhance naturalness. The tool also enables zero-shot voice cloning, allowing speakers to be defined from reference audio samples without requiring dialect-specific training data.

This tool suits projects requiring podcast-style audio generation, particularly those targeting multilingual or multi-dialect audiences. It is most valuable for creators building conversational audio content where speaker diversity and natural speech patterns matter. The zero-shot cross-dialectal voice cloning capability distinguishes it from standard text-to-speech systems, as it allows generating speech in dialects different from the reference speaker's native dialect. Teams working with Mandarin or English content, especially those needing dialectal variation, will find the dialect support particularly relevant.

The project maintains an active demo page and provides model weights through a public collection. A technical report documents the approach and performance characteristics. The codebase is organized as inference code rather than a training framework, indicating focus on deployment and practical use of pre-trained models.