Eleven v3 is ElevenLabs' flagship text-to-speech model. It supports voice cloning, 30+ languages, and fine-grained delivery control for natural-sounding speech generation.

Can I clone a custom voice with Eleven v3?

Yes. Upload voice samples through the ElevenLabs platform, then select the cloned voice on the Audio node in PlugNode. The model generates speech in that voice from any text input.

How does Eleven v3 compare to OpenAI TTS-1 HD?

Eleven v3 offers voice cloning, broader multilingual support, and more granular control over delivery style. TTS-1 HD is simpler to set up with built-in voices and works well for straightforward English narration.

Does PlugNode charge extra for Eleven v3?

No. You pay ElevenLabs directly with your own key. PlugNode does not mark up model costs or run a credit system.

Can I use Eleven v3 for video narration?

Yes. Wire a Text node into Audio (Eleven v3), then combine with a Video node. The flow generates narrated video in one run. Veo handles the footage, Eleven v3 handles the voice.

ElevenLabs · Speech synthesis

Eleven v3

ElevenLabs Eleven v3 on a visual canvas. Clone voices, generate multilingual speech, wire into pipelines, publish as a signed endpoint.

At a glance

Eleven v3 is ElevenLabs' flagship text-to-speech model with voice cloning and multilingual output.
Supports 30+ languages with natural prosody and fine-grained delivery control.
Available on PlugNode as an option on the Audio node. BYO ElevenLabs API key, no markup.
Chain with Gemini or GPT-4.1 for scripted voiceover pipelines.
Pairs with Veo video nodes for narrated video generation in one flow.

What it is

Eleven v3 is ElevenLabs' flagship text-to-speech model. It converts text to speech with support for voice cloning, 30+ languages, and fine-grained control over delivery style, pacing, and emotion. The model produces natural-sounding audio that works for narration, dialogue, and character voices. On PlugNode, Eleven v3 is available on the Audio node. Select it from the model dropdown, choose or upload a voice, pass text input, and the node returns an audio file. It is the strongest option when you need a custom brand voice, multilingual output, or precise delivery. The same Audio node also offers Eleven Flash v2.5 for lower-latency use cases and Eleven Multilingual v2 as a legacy option.

What you can do with it

Convert text to speech with natural prosody and emotion
Clone custom voices from audio samples
Generate speech in 30+ languages
Control delivery style, pacing, and emotion per generation
Chain with GPT-4.1 or Gemini Text for scripted narration
Layer voiceover onto Veo video output in a single flow
Wire into HTTP Trigger and Respond to Webhook for a TTS API

Why Eleven v3 is the default for branded voiceover

Eleven v3 is the strongest option on the Audio node when the voice matters. Voice cloning means you can upload samples of a brand spokesperson, narrator, or character and generate unlimited speech in that voice. The 30+ language support means the same cloned voice can deliver content in multiple languages without re-recording.

On PlugNode, the typical pattern is: Text node generates a script (using GPT-4.1 or Gemini), Audio node (Eleven v3) converts it to speech with the cloned voice, and the output feeds into a Video node or goes directly to a webhook response. The whole pipeline publishes as one endpoint.

Eleven v3 vs Eleven Flash v2.5

Eleven Flash v2.5 is faster and cheaper but trades off some naturalness and voice-cloning fidelity. Use Flash for real-time or near-real-time use cases (live assistants, interactive demos). Use v3 for production content where quality matters more than latency: marketing videos, podcast intros, e-learning modules. Switching between them is a dropdown change on the Audio node.

Run it on PlugNode

Eleven v3 is available on PlugNode's Audio node. Select it from the model dropdown, paste your ElevenLabs API key in Settings, choose a voice (built-in or cloned), and pass text input. No credit system, no markup. Wire it after a Text node for script-to-speech flows, or pair with a Video node for narrated video pipelines.

You pay ElevenLabs directly at their published API rates. PlugNode does not add a per-character markup or a credit layer. Check ElevenLabs pricing page for current rates.

Frequently asked questions

What is Eleven v3?: Eleven v3 is ElevenLabs' flagship text-to-speech model. It supports voice cloning, 30+ languages, and fine-grained delivery control for natural-sounding speech generation.
Can I clone a custom voice with Eleven v3?: Yes. Upload voice samples through the ElevenLabs platform, then select the cloned voice on the Audio node in PlugNode. The model generates speech in that voice from any text input.
How does Eleven v3 compare to OpenAI TTS-1 HD?: Eleven v3 offers voice cloning, broader multilingual support, and more granular control over delivery style. TTS-1 HD is simpler to set up with built-in voices and works well for straightforward English narration.
Does PlugNode charge extra for Eleven v3?: No. You pay ElevenLabs directly with your own key. PlugNode does not mark up model costs or run a credit system.
Can I use Eleven v3 for video narration?: Yes. Wire a Text node into Audio (Eleven v3), then combine with a Video node. The flow generates narrated video in one run. Veo handles the footage, Eleven v3 handles the voice.

Related models

All models

ElevenLabs · Music generationEleven Music v1ElevenLabs Eleven Music v1 on a visual canvas. Generate original music from text, wire into video pipelines, publish as a signed endpoint.

OpenAI · Speech synthesisTTS-1 HDOpenAI TTS-1 HD on a visual canvas. Convert text to speech, wire into media pipelines, publish the flow as a signed endpoint.

OpenAI · Text generationGPT-4.1OpenAI GPT-4.1 on a visual canvas. Generate text, chain it into media pipelines, publish the whole flow as a signed endpoint.

Google · Video generationVeo 3.1Google Veo 3.1 on a visual canvas. Generate 4K video with audio, wire it into a pipeline, publish the whole flow as a signed endpoint.

Last updated 2026-04-28

Generate your first video ad in 3 minutes.

Free to start. No credit card. Upload a product photo, connect your AI models, click Run.