AiselloInstall

Summary

Convert input text into speech using ElevenLabs TTS and render a video combining a source MP4 video with the generated audio, outputting a formatted video file.

Inputs

• Video URL (required) — URL to the source video file (MP4) to use as the video background.
• TTS Text (required) — Text (up to 5000 characters) to convert into speech using ElevenLabs Text-to-Speech.
• Voice ID (required) — ElevenLabs voice ID to use for TTS synthesis, selectable from the ElevenLabs voice library.
• API Key Source (required) — Choice of how to provide the ElevenLabs API key, either manually entered or retrieved from a configured brand.
• ElevenLabs API Key (required) — If manual source selected, the ElevenLabs API key to authenticate TTS requests.
• Brand Name or ID (required) — If API key source is brand, select the brand with ElevenLabs API key configured.
• Format (required) — Output video format preset defining the resolution and aspect ratio, e.g., TikTok 9:16 vertical or YouTube 16:9 horizontal.
• Width (required) — When using the Custom format, the video width in pixels (100-7680).
• Height (required) — When using the Custom format, the video height in pixels (100-4320).
• Options — Optional settings including video duration mode (auto from audio length or custom), specific duration in seconds if custom, encoding quality (low to high), how the source video fits the frame (cover, contain, stretch), and choice of ElevenLabs TTS model.

Output shape

a single JSON object representing the rendered video job response, including URL and metadata of the created video file

The operation returns data containing the rendered video's accessible URL and related metadata. Duration can auto-adjust to the audio length or be custom. Quality affects encoding speed and output file quality.

Links

• n8n community nodes installation guide