Generate speech or a dialogue between two speakers.
Usage and specifics
Supply the required audio input or text and provider credential. Text and audio outputs depend on the operation; preserve MIME types when mapping. Demucs runs locally and needs installed dependencies; remote models depend on account access.
Technical type : generate_speech_google. Runtime : nodulz.
Create credentials in your nodulz instance’s Credentials area, then select them on the node. Availability depends on ownership and sharing. See the credentials guide for access and rotation.
Parameters
Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.
Parameter
Type
Default
Values / limits
credentialId
string
""
-
timeoutSeconds
number
120
-; ≥ 1, ≤ 3600
text
string
""
-
instructions
string
""
-
model
string
"gemini-3.8-flash-tts"
-; min 1, max 128
voice
string
"Kore"
-; min 1
speakers
array
[]
-; max 2
speakers[].name
string
-
-; min 1, max 100
speakers[].voice
string
-
-; min 1, max 100
Configuration help
credentialId AI credential
{provider} API credential accessible to the workflow owner. The provider bills API requests.
speakers Two-speaker dialogue
Configure two distinct speaker names and voices. Identify speakers in the text, for example Joe: Hello. Jane: Hi.
timeoutSeconds Timeout (seconds)
Maximum AI request time, within the overall workflow timeout.
Initial configuration
Initial catalog configuration example, to adapt before running. Keep secrets in credentials.
Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.
Generate speech or a dialogue between two speakers.
Usage and specifics
Supply the required audio input or text and provider credential. Text and audio outputs depend on the operation; preserve MIME types when mapping. Demucs runs locally and needs installed dependencies; remote models depend on account access.
Technical type :
generate_speech_google. Runtime :nodulz.Credentials and prerequisites
Create credentials in your nodulz instance’s Credentials area, then select them on the node. Availability depends on ownership and sharing. See the credentials guide for access and rotation.
Parameters
Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.
credentialIdstring""timeoutSecondsnumber120textstring""instructionsstring""modelstring"gemini-3.8-flash-tts"voicestring"Kore"speakersarray[]speakers[].namestringspeakers[].voicestringConfiguration help
credentialIdAI credential
speakersTwo-speaker dialogue
timeoutSecondsTimeout (seconds)
Initial configuration
Initial catalog configuration example, to adapt before running. Keep secrets in credentials.
{ "credentialId": "", "timeoutSeconds": 120, "text": "", "instructions": "", "model": "gemini-3.8-flash-tts", "voice": "Kore", "speakers": [] }Verification
Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.
See also : Expressions and data, Executions, Node catalog.