# Docs

- [ListenHub Skills](/docs/en/skills): Let your AI Agent turn ideas into podcasts, explainer videos, speech, and images.
- [Getting Started](/docs/en/skills/getting-started): Install ListenHub Skills and generate your first content in under 5 minutes.
- [Creator](/docs/en/skills/creator): Generate multi-platform content packages — articles, image cards, or narration scripts with illustrations and audio — from any topic, URL, or audio file.
- [Updating Skills](/docs/en/skills/updating): Keep ListenHub Skills up to date. Instructions for users and AI Agents.
- [ListenHub Voice](/docs/en/skills/listenhub-voice): Generate audio end to end with ListenHub-Voice-1.0 — narration, sound effects, multi-voice dialogue, voice cloning, or image-to-audio, from a single text script.
- [Podcast](/docs/en/skills/podcast): Generate podcast episodes with AI — solo narration, two-host dialogue, or debate format — from any topic, URL, or text.
- [Explainer Video](/docs/en/skills/explainer): Create narrated explainer videos with AI-generated visuals from a topic, URL, or text, in info or story mode.
- [TTS](/docs/en/skills/tts): Convert text to natural-sounding speech — quick single-voice narration or smart multi-speaker dialogue from a script.
- [Speech Recognition (ASR)](/docs/en/skills/asr): Transcribe audio files to text locally with the coli CLI — multilingual, with optional AI polish, fully offline, no API key.
- [Image Generation](/docs/en/skills/image): Generate AI images from text prompts with optional reference images, choosing the pro or flash model and any supported aspect ratio.
- [Music](/docs/en/skills/music): Generate, remix, extend, and analyze AI music with Mureka — songs, instrumentals, soundtracks, stems, and lyrics.
- [Video Generation](/docs/en/skills/video-gen): Generate AI videos from text, images, or reference media — with image-to-video, video editing, and PixVerse lip sync.
- [Slides](/docs/en/skills/slides): Create slide decks with AI-generated visuals from a topic, URL, or text, with optional voice narration.
- [Content Parser](/docs/en/skills/content-parser): Extract and parse content from any URL — articles, videos, tweets, PDFs, and more — with optional summarization and length limits.
- Advanced: undefined
  - [Multi-Voice Scripts](/docs/en/skills/advanced/tts): Use a JSON script to control which voice speaks each line, for multi-character dialogue and dramatised scripts.
  - [Script-First Podcast](/docs/en/skills/advanced/script-first-podcast): Generate the script first, review and edit it, then render audio — turning podcast production into a controllable two-stage process.
  - [Reference Image](/docs/en/skills/advanced/reference-image): Supply a reference image as a style anchor so the AI can learn the look and generate new variants.
- Guides: undefined
  - [Composing Skills](/docs/en/skills/guides/composing-skills): Chain multiple skills together for complex workflows — parse URLs, generate podcasts, add visuals.
  - [Best Practices](/docs/en/skills/guides/best-practices): Tips for getting better results — prompt writing, quality optimization, and common patterns.
- [Help & FAQ](/docs/en/skills/help): Common questions, troubleshooting, and how to get help.

# Docs

- [MCP Server](/docs/en/mcp): Use ListenHub's audio generation as MCP tools inside Claude Desktop, Cursor, and other MCP clients.
- [Quick Start](/docs/en/mcp/quick-start): Install Node.js, get an API key, and connect the ListenHub MCP server to your client.
- [Usage Examples](/docs/en/mcp/usage-examples): Prompt-to-tool-call walkthroughs for podcasts, FlowSpeech, the script-first flow, speaker discovery, and account checks.
- [Core Capabilities](/docs/en/mcp/core-capabilities): What the ListenHub MCP server can do — podcast and FlowSpeech generation, speaker lookup, and account checks.
- [Transport Modes](/docs/en/mcp/transport-modes): Run the ListenHub MCP server over stdio (default) or HTTP, and choose the right one for your client.
- [Available Tools](/docs/en/mcp/available-tools): The 8 ListenHub MCP tools, their input constraints, and the response shape each one returns.

# Docs

- [ListenHub OpenAPI](/docs/en/openapi): Transform everything into podcasts, speech, music, images, and videos with a single API call.
- [Quick Start](/docs/en/openapi/quick-start): Get your API key and make your first call in 5 minutes.
- [Core Concepts](/docs/en/openapi/concepts): Episodes, speakers, generation modes, and data flow in ListenHub OpenAPI.
- [Authentication & Security](/docs/en/openapi/authentication): Base URL, API key usage, and request limits.
- API Reference: undefined
  - [Speakers](/docs/en/openapi/api-reference/speakers): Retrieve all available voices including cloned speakers for use in Podcast, Text to Speech, and other generation APIs.
  - [ListenHub Voice](/docs/en/openapi/api-reference/listenhub-voice): Turn text, reference voices, or an image into speech and sound effects with end-to-end async generation, then poll the task for the finished audio.
  - [Voice Cloning](/docs/en/openapi/api-reference/voice-clone): Upload reference audio to create a reusable private voice, confirm it, and use its speaker ID with the speech and TTS endpoints.
  - [Podcast](/docs/en/openapi/api-reference/podcast): Generate single or dual-speaker podcast episodes — one-shot or split into a script-then-audio workflow — with quick, deep, and debate modes.
  - [Explainer Video](/docs/en/openapi/api-reference/explainer-video): Turn any content into narrated explainer videos with AI-generated visuals and voiceover.
  - AI Video: undefined
    - [AI Video](/docs/en/openapi/api-reference/ai-video): Generate short AI videos asynchronously across Seedance, HappyHorse, and PixVerse models from text, image, video, and audio inputs.
    - [Seedance](/docs/en/openapi/api-reference/ai-video/seedance): Seedance-specific models, limits, and pricing notes for the shared AI Video generation endpoint.
    - [HappyHorse](/docs/en/openapi/api-reference/ai-video/happyhorse): HappyHorse-specific model, limits, and constraints for the shared AI Video generation endpoint.
    - [PixVerse Video](/docs/en/openapi/api-reference/ai-video/pixverse): Create PixVerse AI video tasks across nine capabilities — text-to-video, image-to-video, transitions, fusion, restyle, mimic, lip sync, and marketing agents.
  - [Slides](/docs/en/openapi/api-reference/slides): Generate AI-powered presentation slides with visuals and voiceover scripts, ready for meetings and reports.
  - [Text to Speech](/docs/en/openapi/api-reference/flowspeech): Convert text to natural-sounding speech across five endpoints, from low-latency single-voice streaming to long-form async narration.
  - [Music Generation](/docs/en/openapi/api-reference/music): Generate songs, instrumentals, and soundtracks with Mureka, and analyze existing audio — lyrics recognition, description, and stem separation.
  - [Image Generation](/docs/en/openapi/api-reference/image-generation): Generate AI images from text prompts and reference images, synchronously or as async tasks, with credit estimation.
  - [Content Extract](/docs/en/openapi/api-reference/content-extract): Asynchronously extract text content from URLs including web articles, Twitter/X profiles, tweets, YouTube videos, and WeChat Official Account posts.
  - [Subscription](/docs/en/openapi/api-reference/subscription): Query account subscription status, credit balances, and expiration details.
- [Error Handling](/docs/en/openapi/errors): Error code reference and troubleshooting guide.
- [Credits & Pricing](/docs/en/openapi/pricing): Credit types, consumption reference, and rate limits.
- [Support](/docs/en/openapi/support): Contact information, FAQ, and glossary.

# Docs

- [SDKs & CLI](/docs/en/tools): Official JavaScript/TypeScript SDK and command-line tool for the ListenHub API, plus guidance on when to use each.
- JavaScript SDK: undefined
  - [JavaScript SDK](/docs/en/tools/sdk): A typed JavaScript/TypeScript client for the ListenHub API, with two clients for API-key and OAuth authentication.
  - [Quickstart](/docs/en/tools/sdk/quickstart): Install the SDK, authenticate with an API key, create a podcast, poll until it finishes, and read the audio URL.
  - [Authentication](/docs/en/tools/sdk/authentication): Authenticate the SDK with an API key for server-side work, or with OAuth user tokens when acting on a signed-in user's behalf.
  - [Configuration](/docs/en/tools/sdk/configuration): Configure base URL, timeout, and retries for both SDK clients, and learn how response unwrapping, ListenHubError, and 429 auto-retry behave.
  - [SDK Reference](/docs/en/tools/sdk/reference): Every method on OpenAPIClient and ListenHubClient, grouped by product, with signatures, endpoints, and what each returns.
  - [Examples](/docs/en/tools/sdk/examples): Eight runnable TypeScript recipes for the OpenAPIClient — podcast, flow speech, TTS, image, video, music, content extract, and error handling.
- CLI: undefined
  - [CLI](/docs/en/tools/cli): Create podcasts, speech, images, music, and video from your terminal — OAuth for interactive use, an API key for scripts and CI.
  - [CLI Quickstart](/docs/en/tools/cli/quickstart): Install the CLI, authenticate, and create your first podcast from the terminal in a few minutes.
  - [Authentication](/docs/en/tools/cli/authentication): Log in with browser OAuth for interactive use, or configure an API key for scripts and CI — and switch between them.
  - [OAuth Commands](/docs/en/tools/cli/commands): Full reference for the listenhub OAuth commands — auth, podcast, tts, explainer, slides, music, image, video, speakers, lyrics, and creation.
  - [OpenAPI Commands](/docs/en/tools/cli/openapi-commands): Reference for every `listenhub openapi` command — the API-key namespace for scripts and CI.
  - [CLI Examples](/docs/en/tools/cli/examples): Copy-pasteable shell recipes for one-shot generation, batch loops, audio export, and CI pipelines with the listenhub CLI.

# Data

- [Voice catalogue](/voices.txt): Every official ListenHub voice as plain text — speakerId, name, language, gender, access and tags, in one request and with no API key. The speakerId is what selects a voice in ListenHub Skills, the MCP server, the CLI (`--speaker-id`) and the API (`scripts[].speakerId`).