Camb.ai icon

Camb.ai

Use Camb.ai for TTS, transcription, translation, voice cloning, and more

Actions9

Voice → Create From Description

AI-generated

Summary

Create a synthetic voice from a text description via Camb.ai

Inputs

  • text (required) — Sample text the synthetic voice will speak
  • voiceDescription (required) — Detailed description of desired voice (minimum 18 words / 100+ characters)
  • binaryPropertyName (required) — The name of the output binary field to put the voice preview audio in

Output shape

Each processed item returns a JSON object with task metadata and two binary audio previews attached to the specified field name.

The operation calls the Camb.ai /text-to-voice endpoint, polls for task completion, then downloads two preview audio files (MP3) as binary data. Voice description must be at least 100 characters (18+ words); otherwise a validation error is thrown.

Examples

Example 1: Generate a voice preview from a description

Set text to a sample sentence, voiceDescription to a detailed accent/tonal profile (100+ chars), and binaryPropertyName to a field like myVoiceAudio. The node returns the task ID, run ID, the original description, and two MP3 preview URLs/files in the specified binary field.

Links

Discussion