LeanVoxInstall

Summary

Generates speech from text asynchronously via the LeanVox API.

Inputs

• text (required) — The text to convert to speech.
• model (required) — The TTS model to use. Standard: fast & lightweight. Pro: 238 curated voices with cloning. Max: instruction-based voice design.
• voice (required) — The voice ID to use for synthesis.
• language — Optional language code (e.g., en, es, fr).
• voiceInstructions — Custom voice instructions (only valid with model 'max').

Output shape

a single record

Returns a JSON object with an audio_url property containing the generated audio file URL.

Examples

Example 1: Quick synthesis with standard settings

Text: 'Hello world', Model: 'standard', Voice: 'default_voice_id', Language: 'en'

Example 2: Pro voice cloning synthesis

Text: 'Read this script', Model: 'pro', Voice: 'cloned_voice_id', Language: 'en'

Example 3: Instruction-based voice design

Text: 'Read this script', Model: 'max', Voice: 'custom_voice_id', Voice Instructions: 'Speak slowly and warmly'

Links

• n8n community nodes installation guide