Back to Nodes
ElevenLabs TTS V3

ElevenLabs TTS V3

Official

Generate high-quality text-to-speech audio using ElevenLabs' advanced Eleven-v3 model. Customize voice, stability, speed, and more.

Nodespell AI
AI / Audio / Elevenlabs

Generate high-quality text-to-speech audio using ElevenLabs' advanced Eleven-v3 model. Customize voice, stability, speed, and more.

Model Overview

Text-to-audio converter that generates realistic and expressive speech from text using the ElevenLabs Eleven-v3 model.

Best At

Creating natural-sounding voiceovers for audiobooks, narrations, and interactive applications. Offers extensive voice customization options to match desired tones.

Limitations / Not Good At

Limited language support (only English currently). May struggle with highly non-standard pronunciation or complex emotional tones beyond predefined voices.

Ideal Use Cases

Website voiceovers, video narration, interactive voice assistants, and custom audio content creation.

Input & Output Format

Input: Text string and optional voice parameters. Output: Audio file in MP3 format and optional word-level timestamps.

Performance Notes

On-demand generation with response times scaling with text length. Continuous speech options (previous_text, next_text) improve consistency for long audio streams.

Model Examples (4)

Example Index01 / 04
Example 01

Prestige-series teaser

Trailer-style narration for a dramatic series promo.

Open
Source Inputs01
Text

At first they called it an accident. Then the dailies came back. Every frame showed the same door, open three inches wider than before. This autumn, the footage tells its own story.

Parameters06
Text
At first they called it an accident. Then the dailies came back. Every frame showed the same door, open three inches wider than before. This autumn, the footage tells its own story.
Voice
JBFqnCBsd6RMkjVDRZzb
Speed
1
Style
0.2
Stability
0.45
Similarity Boost
0.75
ttstrailer
Response
Inputs (3)

Text

String

The text to convert to speech

Multi InputMin: 0Max: 100

Previous Text (Optional)

String

The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

Multi InputMin: 0Max: 100

Next Text (Optional)

String

The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

Multi InputMin: 0Max: 100
Parameters (11)

Text

String

The text to convert to speech

Default:

Next Text

String

The text that comes after the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

Default:

Speed

Number

Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality.

Default: 1

Style

Number

Style exaggeration (0-1): Amplifies the distinctive speaking style of the original voice. It adds extra effort and latency, and can make the output slightly less stable, so it’s best kept at 0 unless a dramatic effect is needed.

Default: 0

Stability

Number

Voice stability (0-1): Controls how consistent the voice is. Lower values give a wider emotional range and more varied pacing, but can sound erratic. Higher values produce a steadier, more monotone delivery that usually requires fewer iterations to hit the desired tone.

Default: 0.5

Similarity Boost

Number

Similarity boost (0-1): The similarity slider dictates how closely the AI should adhere to the original voice when attempting to replicate it. If the original audio is of poor quality and the similarity slider is set too high, the AI may reproduce artifacts or background noise when trying to mimic the voice if those were present in the original recording.

Default: 0.75

Voice

String

The voice to use for speech generation

Default: 21m00Tcm4TlvDq8ikWAM

Language Code

String

Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5 and Flash v2.5 support language enforcement. For other models, an error will be returned if language code is provided.

Default:

Previous Text

String

The text that came before the text of the current request. Can be used to improve the speech's continuity when concatenating together multiple generations or to influence the speech's continuity in the current generation.

Default:

Voice Control

String
Default:

Advanced

String
Default:
Outputs (1)

Output

Inferred

Output

Nodespell

Nodespell

London

Building the future. Join us!

nodespell.comnodespell.appNodespellAI
Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Audio / Elevenlabs

Input

Text

Output

Audio

Keywords

Length ControlMulti Output
Use in Workflow