ElevenLabs TTS (Custom Voice)

Generate speech with your custom cloned voice_id. Returns audio + word-level timestamps for kinetic captions, collage sync, and screen-rec alignment.

Try ElevenLabs TTS (Custom Voice) in the playground

Last updated View as MarkdownAgent setup

ElevenLabs TTS (Custom Voice)

Badge: Direct
Node type: audio:elevenlabs_tts_custom_voice
Category: audio

Description

ElevenLabs TTS (Custom Voice) speaks a script in a voice you cloned and returns word-level timestamps with the audio: wire text into Text, connect the ElevenLabs Voice Clone node to ElevenLabs Voice ID (or pick one of your cloned voices, or paste a 20-character voice_id), and run the node. The Word Timestamps output is JSON, made for kinetic captions, collage sync and lining speech up with a screen recording. Under Model, pick a version such as eleven_multilingual_v2, eleven_flash_v2_5, eleven_v3 or eleven_v4. The v4 and v4 Turbo models take inline audio tags such as [whispering] or [chuckles], and on v4 only Stability and Similarity apply.

Pricing

  • Cost: priced by the length of the text it speaks: 3 credits for 100 characters, 20 for 1,000, 40 for 2,500 and 80 for the 5,000-character maximum. Longer text is refused before you are charged.

Canvas ports

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

ID Label Details
text Text TEXT (required)
voice_id ElevenLabs Voice ID TEXT (required) — Connect the ElevenLabs Voice Clone node, pick one of your cloned voices, or paste a voice_id (20-char alphanumeric, e.g. U4EYshq59eo7K2i5yWVR).

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

ID Label Details
model_id Model TEXT · options: eleven_multilingual_v2, eleven_turbo_v2_5, eleven_flash_v2_5, eleven_v3, eleven_v4, +1 — v4 and v4 Turbo take inline audio tags such as [confident], [pauses], [chuckles], [whispering]. On v4 only Stability and Similarity apply; Style, Speed and Speaker Boost are not sent.
stability Stability NUMBER · 0…1
similarity_boost Similarity Boost NUMBER · 0…1
style Style NUMBER · 0…1
speed Speed NUMBER · 0.7…1.2
use_speaker_boost Speaker Boost BOOLEAN

Outputs

ID Label Type
audio 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.