Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery. Includes single scene regeneration for fine

ElevenLabs Voiceover Generation Generate professional AI voiceovers for Remotion videos using ElevenLabs API. Prerequisites ELEVENLABS API KEY in .env.local Quick Start Character Presets Use character presets for more natural voiceovers instead of literal screen text reading: Character Description Best For literal Reads text exactly as written Screen text, quotes narrator Professional storyteller, smooth, engaging Explainers, documentaries salesperson Enthusiastic, persuasive, energetic Marketing, ads expert Authoritative, confident, knowledgeable Legal content, tutorials conversational Casual, friendly, natural Social media, casual content dramatic Intense, emotional, impactful Hooks, problem statements calm Soothing, reassuring, gentle Trust building, conclusions Scene Based Generation with Request Stitching Generate multiple scenes with consistent prosody using ElevenLabs request stitching: scenes.json Format Generate All Scenes This creates: product demo scene1.mp3 through sceneN.mp3 product demo combined.mp3 (all scenes stitched) product demo info.json (metadata with durations) Single Scene Regeneration If a scene starts too early, has wrong timing, or needs different text: The tool automatically: Uses request stitching from previous scenes for consistent prosody Updates the info.json file with new metadata Updates scenes.json if new text is provided Thumbnail Embedding Embed a thumbnail image into MP4 videos so platforms like Twitter, YouTube, and video players display your custom thumbnail instead of the first frame. Embed Thumbnail into Video Workflow with Remotion Supported Formats Video : MP4 (H.264/H.265) Thumbnail : PNG, JPG, JPEG The embedding uses ffmpeg's disposition:v:1 attached pic flag to set the thumbnail as an attached picture, which most video players and platforms recognize. Timing Validation The skill automatically validates timing after generation using ffprobe : What It Checks Check Threshold Description Duration mismatch 15% Warns if actual differs from expected duration Leading silence 200ms Audio starts late (voiceover delayed) Trailing silence 500ms Unnecessary silence at end Speaking rate 2 4.5 wps Optimal ~3 words/second Validate Existing Audio Output example: Updated info.json After validation, the info.json includes actual measurements: Use actualDuration in your Remotion composition for precise sync. Options Option Description Default text , t Text to convert to speech Required (or file/ scenes) file , f Read text from file output , o Output file path output.mp3 output dir Output directory for scenes public/audio voice , v Voice name or ID George model , m Model ID eleven multilingual v2 character , c Character preset literal scenes JSON file with scenes scene Regenerate single scene ID new text New text for scene regen validate Validate existing audio dir skip validation Skip auto validation false embed thumbnail Video file to embed thumbnail into thumbnail Thumbnail image file (PNG/JPG) stability Voice stability (0 1) varies by character similarity Voice similarity (0 1) varies by character style Style exaggeration (0 1) varies by character no combined Skip combined file false Recommended Voices Voice Style Best For George Warm, captivating British Narration, explainers Antoni Professional, warm Legal content, tutorials Arnold Authoritative, deep Corporate, serious topics Josh Friendly, conversational Marketing, casual content Integration with Remotion After generating scene voiceovers, use them in your composition: Tips for Best Results 1. Use character presets : Don't read screen text literally use narrator or expert for natural flow 2. Punctuation matters : Use periods for pauses, commas for brief breaks 3. Numbers : Write out numbers ("five hundred" not "500") for natural speech 4. Abbreviations : Write full words ("twenty four hours" not "24h") 5. Scene by scene : Different scenes can have different characters (dramatic intro, calm CTA) 6. Fine tune : Use scene to regenerate individual scenes without redoing everything 7. Request stitching : Keeps voice consistent across all scenes Workflow Example

elevenlabs-remotion