Core Capabilities

Podcast generation
- Supports full generation (text + audio) or text-only generation
- Supports 1 to 2 speakers with customizable voices
- Provides multiple generation modes: quick, deep, and debate
- Supports two-stage generation flow
- Accepts text and URL as content sources
- Supports podcast status querying
- Returns audio file, title, scripts, outline, and related metadata
- Tracks credit usage
FlowSpeech generation
- Converts text or URL content into conversational single-speaker audio
- Supports smart mode (AI-enhanced narration) and direct mode (verbatim reading)
- Supports FlowSpeech status querying
- Returns audio file, title, scripts, outline, and related metadata
- Tracks credit usage
Voice management
- Browse available voices library
- Filter by language and voice attributes
- Retrieve voice ID, name, language, gender, and demo audio
User account information
- Check subscription status and plan details
- View credit usage by monthly, permanent, and limited-time credits
- Monitor total available credits and renewal status
- View subscription start and expiration dates
Multiple transports
- Supports Stdio, HTTP SSE, and HTTP Streamable transport for flexible integration