Chapter 676: Transcribing audio

Core Idea

Remotion provides several built-in options for transcribing audio to generate captions:

Key Concepts

• Comparison
• The Caption type
• Alternatives
• See also

Reference Tables

	@remotion/install-whisper-cpp	@remotion/whisper-web	@remotion/openai-whisper	@remotion/elevenlabs
Environment	Server (Node.js)	Client (Browser)	Cloud (API)	Cloud (API)
Speed	Fast (depends on hardware)	Slow (WASM overhead)	Fast	Fast
Cost	Free	Free	Paid (OpenAI API pricing)	Paid (ElevenLabs API pricing)
Offline support	✅	✅	❌	❌
No server needed	❌	✅	✅	✅
Convert function	toCaptions()	toCaptions()	openaiWhisperApiToCaptions()	elevenLabsTranscriptToCaptions()

Key Takeaways

1. Understand comparison when working with Transcribing audio.
2. Understand the caption type when working with Transcribing audio.
3. Understand alternatives when working with Transcribing audio.
4. Understand see also when working with Transcribing audio.

Connects To

• api: related page in the Captions (@remotion/captions) section.
• Caption: related page in the Captions (@remotion/captions) section.
• Create Tiktok Style Captions: related page in the Captions (@remotion/captions) section.