Setup & Installation
npx skills add https://github.com/fal-ai-community/skills --skill fal-audio
https://github.com/fal-ai-community/skills/tree/main/skills/claude.ai/fal-audio
View on GitHubWhat This Skill Does
Converts text to speech and transcribes audio to text using fal.ai's audio models. Supports multiple TTS engines like MiniMax and ElevenLabs, plus Whisper-based transcription with optional speaker diarization and multi-language support.
Handles both TTS and STT through one interface with access to multiple model providers, so you don't need separate accounts or scripts for each.
When to use it
- Generating voiceovers for short videos or presentations
- Transcribing recorded meetings with speaker identification
- Converting blog posts into audio format for listeners
- Adding multilingual narration to product demos
- Getting text transcripts from podcast episodes