ElevenLabs TTS

ElevenLabs TTS is the voice model for narration and standalone audio when no generated face needs to lip-sync on screen.

First video free, no card

When to use it

Pick it when you need a clean voice track and no face.

Best for

  • voiceover on b-roll
  • narration
  • a standalone voice file
  • an audio reference for generate_video

Avoid for

  • lip-synced talking head, where generate_video renders speech natively

Modes

  • text-to-speech

Prompt notes

  • Use emotion tags like [excited] or [whispers] when you need delivery cues.

  • Keep sentences short for pacing.

  • Use a named voice or raw ElevenLabs voice id when your workflow requires a specific voice.

Related use cases

FAQ

When should I use ElevenLabs TTS?
Use it for narration, b-roll voiceover, standalone audio, or an audio reference.
Should I use it for talking-head video?
Usually no. For lip-synced talking-head clips, generate_video renders speech natively.
Can the audio become a video reference?
Yes. Use the audio output as an audio reference in supported video workflows.

What do you sell?

First video free, no card