ElevenLabs TTS

ElevenLabs v3 Text-to-Speech, expressive, natural speech with inline audio tags like [laughs], [whispers], [excited], [sighs], [sad], [angry]. Supports 70+ languages.

Try ElevenLabs TTS in the playground

Last updated View as MarkdownAgent setup

ElevenLabs TTS

Badge: v3
Node type: audio:elevenlabs_tts_eleven_v3
Category: audio

Description

ElevenLabs v3 Text-to-Speech, expressive, natural speech with inline audio tags like [laughs], [whispers], [excited], [sighs], [sad], [angry]. Supports 70+ languages.

Pricing

  • Cost: ~20 credits per 1000

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
text Text TEXT (required)
language_code Language Code TEXT

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
voice Voice TEXT · options: Rachel, Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill · default: "Rachel"
stability Stability NUMBER · 0…1 · default: 0.5
timestamps Word Timestamps BOOLEAN · default: false
apply_text_normalization Text Normalization TEXT · options: auto, on, off · default: "auto"

Outputs

ID Label Type
audio Generated Audio AUDIO
word_timestamps Word Timestamps JSON

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.