Overview

Generate speech audio from a prompt when a trigger or event occurs and save locally or play via SIP.

Text to Speech

This node generates an audio file from a text prompt when a trigger or event occurs. The audio is saved locally on the filesystem, and the node outputs metadata indicating whether a new audio file was generated.

Inputs & Outputs

Input media: Raw Video.
Output media: Raw Video.
Output metadata: nodes.node_id.audio_generated_delta.

Properties

Property	Description	Type	Default	Required
`trigger_source`	Generate audio from events generated by other nodes or a custom defined trigger. Options: Events from previous nodes (`built_in`); Custom Trigger (`custom`).	`enum`	`custom`	Yes
`trigger`	Generate audio when this condition evaluates to true. Conditional on `trigger_source` being `custom`.	trigger-condition	`null`	Yes
`interval`	Min. time between consecutive generations. Unit: seconds.	`float`	`10`	No
`enabled`	Enabled	`bool`	`true`	No
`prompt_source`	Prompt Source. Options: Static prompt (`static`); Metadata path (`metadata_path`).	`enum`	`static`	Yes
`prompt_text`	Static Prompt. Conditional on `prompt_source` being `static`.	`string`	`""`	No
`prompt_metadata_path`	Comma-separated metadata paths to extract prompt text. Conditional on `prompt_source` being `metadata_path`. Format: comma-separated metadata paths or patterns.	`string`	`""`	No
`tts_provider`	TTS Provider. Options: Lumeo Cloud (`lumeo`); ElevenLabs Cloud (`elevenlabs`).	`enum`	`lumeo`	Yes
`lumeo_voice_id`	Voice. Options: Male (`male`); Female (`female`). Conditional on `tts_provider` being `lumeo`.	`enum`	`male`	Yes
`elevenlabs_api_key`	ElevenLabs API Key. Conditional on `tts_provider` being `elevenlabs`.	`string`	`null`	Yes
`elevenlabs_voice_id`	ElevenLabs Voice ID. Conditional on `tts_provider` being `elevenlabs`.	`string`	`DXFkLCBUTmvXpp2QwZjA`	Yes
`elevenlabs_model_id`	ElevenLabs Model ID. Conditional on `tts_provider` being `elevenlabs`.	`string`	`eleven_flash_v2_5`	No
`audio_format`	Audio Format. Options: MP3 (`mp3`); WAV (`wav`).	`enum`	`mp3`	No
`sip_enabled`	When enabled, plays the generated audio to a SIP endpoint (e.g. a Hanwha speaker) via RTP. Audio format is forced to WAV when SIP is enabled.	`bool`	`false`	Yes
`sip_ip`	SIP Endpoint IP. Conditional on `sip_enabled` being `true`.	`string`	`""`	Yes
`sip_port`	SIP Port. Conditional on `sip_enabled` being `true`.	`number`	`5060`	Yes
`sip_username`	SIP user/extension on the endpoint. Conditional on `sip_enabled` being `true`.	`string`	`51`	Yes
`sip_password`	SIP password (optional, for future digest auth support). Conditional on `sip_enabled` being `true`.	`string`	`""`	No

When SIP output is enabled, audio format is automatically forced to WAV. The node establishes a SIP call to the endpoint, streams the audio as G.711 u-law over RTP, then terminates the call.

Output Metadata

The fields below are declared by this node's metadata schema; the JSON values are representative examples.

Path	Type	Description
`nodes.<node_id>.audio_generated_delta`	`boolean`	When audio is generated
`nodes.<node_id>.audio_filepath`	`string`	The filepath of the audio file generated, present when audio is generated
`nodes.<node_id>.type`	`string`	Identifies the node type that produced this metadata.

JSON example

{
  "nodes": {
    "text_to_speech1": {
      "audio_filepath": "/path/to/output",
      "audio_generated_delta": false,
      "type": "text_to_speech"
    }
  }
}