← Node reference

Text to Speech

AI generationElevenLabs

ElevenLabs voiceover from text. Pick a voice and type the line; outputs spoken audio for lip-sync or mixdown.

Runs
On our servers
Typical time
3-15s
Inputs
1
Outputs
1

Inputs

PortTypeID
Prompttextprompt-in

Outputs

PortTypeID
Audioaudioaudio-out

Settings

SettingTypeDefaultOptions
VoiceElevenLabs voiceselectMatildaMatilda (warm young female), Jessica (expressive young female), Sarah (soft young female), Alice (clear female), Lily (gentle female), Aria (mature female), Brian (warm male), Will (friendly male), Eric (mid male), George (warm male), Daniel (deep male)
StabilityLower = more emotional range, higher = more consistentselect0.45Expressive (0.3), Natural (0.45), Steady (0.6)

Prompting

Type the words to speak...

Maximum prompt length: 1000 characters.

What this connects into (5)

Computed from the port compatibility rules, so it stays correct as nodes change.

Node ID elevenlabs-tts. Open it in Studio with Tab, then type the name.