ElevenLabs text to speech

Give every scene a voice with a voice ID.

Use ElevenLabs text to speech inside Start The Vision for expressive narration, character dialogue, and production-ready audio. Bring any supported ElevenLabs voice into your workflow with its voice ID.

Built for real production

A focused workflow from idea to final output.

Use supported ElevenLabs voices through their voice IDs.

Create narration, dialogue, and character performances from text.

Keep audio generation close to your video and image work.

Plan voice usage with monthly voice credit packages.

Available models

Choose the model that fits the job.

Eleven Flash (v2.5)

Fast generation

eleven_flash_v2_5

Eleven Multilingual V2

Multilingual speech

eleven_multilingual_v2

Eleven Turbo (v2.5)

Low latency

eleven_turbo_v2_5

Eleven V3

Latest

Latest model

eleven_v3

This list is maintained from the shared model catalog so model information stays consistent across the public site and studio.

How it works

Make the next version of your idea.

01

Choose a voice ID

Bring the ElevenLabs voice you want to use into the generation workflow.

02

Write the performance

Add the narration or dialogue and shape the tone through your text and settings.

03

Listen and refine

Review the audio, copy the prompt when needed, and keep your strongest take.

Frequently asked

Answers before you start.

Are all ElevenLabs voices supported?

The page is designed around supported ElevenLabs voice IDs. Availability can depend on the voice ID and the connected ElevenLabs account or API access.

Which ElevenLabs model is selected by default?

Eleven V3 is the latest recommended model in the shared model catalog. The available list also includes Eleven Flash (v2.5), Eleven Multilingual V2, and Eleven Turbo (v2.5).

Can I use this for character dialogue?

Yes. It is suitable for narration, dialogue, explainers, and character voice production.