skillfed

happy-audio-gen

happy-audio-gen synthesizes natural speech from any text across six major TTS providers through a single interface. Route here whenever users ask to read text aloud, create narration, dub scripts, or generate voice-overs—the skill auto-detects available credentials and handles long-form content by chunking transparently. Output formats include MP3, WAV, OGG, and FLAC.

happy-audio-gen converts text to speech across six providers including OpenAI, ElevenLabs, and Bailian with automatic long-text handling.

AI-generated summary based on this skill's SKILL.md

305 29 MIT updated by iamzhihuix

Install

iamzhihuix/happy-claude-skills/happy-audio-gen · repository language: TypeScript

CLI (skillfed)coming soon
git clone https://github.com/iamzhihuix/happy-claude-skills
cp -r happy-claude-skills/skills/happy-audio-gen ~/.claude/skills/happy-audio-gen

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

Can happy-audio-gen convert text to speech?

Yes. happy-audio-gen synthesizes natural-sounding speech from any written text through a unified interface connecting six major TTS providers. The skill auto-detects your available credentials and outputs MP3, WAV, OGG, or FLAC formats.

How does happy-audio-gen handle long-form content?

happy-audio-gen processes long-form text by automatically chunking it into manageable segments, so you can convert entire articles, documents, or scripts into audio without manual splitting. The chunking happens transparently in the background.

Does happy-audio-gen support multiple languages and voice cloning?

Yes. happy-audio-gen synthesizes speech in multiple languages and supports voice cloning synthesis, letting you generate narration with custom voices across different language pairs.

Can I generate voice-over or narration for content using happy-audio-gen?

Absolutely. happy-audio-gen generates voice-over and narration for any content—whether you're dubbing scripts, creating narration audio, or producing voice-overs. Route text or scripts here and the skill produces natural-sounding audio files.

What output formats does happy-audio-gen support?

happy-audio-gen outputs MP3, WAV, OGG, and FLAC formats, giving you flexibility to use the generated audio across different platforms and applications.

How does happy-audio-gen access multiple TTS providers?

happy-audio-gen connects to six major TTS providers through a single unified interface. It auto-detects which provider credentials you have available and routes your requests accordingly, simplifying multi-provider access.

SKILL.md

rendered from the published skill — quoted content, verbatim

happy-audio-gen

Turns text into speech across 6 providers through one CLI. All providers are synchronous (TTS is fast — typically under 10 seconds) except Bailian's voice-design flow (which is still covered but uses a longer poll window).

Quick usage

```bash

Shortest path —

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 15 files
skills/happy-audio-gen/SKILL.md
skills/happy-audio-gen/assets/EXTEND.template.md
skills/happy-audio-gen/package.json
skills/happy-audio-gen/references/config/extend-schema.md
skills/happy-audio-gen/references/config/first-time-setup.md
skills/happy-audio-gen/references/error_codes.md
skills/happy-audio-gen/references/providers.md
skills/happy-audio-gen/references/voices.md
skills/happy-audio-gen/scripts/main.ts
skills/happy-audio-gen/scripts/providers/bailian.ts
skills/happy-audio-gen/scripts/providers/elevenlabs.ts
skills/happy-audio-gen/scripts/providers/minimax.ts
skills/happy-audio-gen/scripts/providers/openai.ts
skills/happy-audio-gen/scripts/providers/playht.ts
skills/happy-audio-gen/scripts/providers/siliconflow.ts

Related skills

Tags

voice-synthesis audio-output multi-provider script-narration voice-cloning long-text-handling multilingual-support batch-processing voice-customization format-conversion