Back to Nodes
Resemble AI Chatterbox

Resemble AI Chatterbox

Official

Expressive speech generation with optional audio prompt guidance.

Nodespell AI
AI / Audio / Resemble Ai

Expressive speech generation with optional audio prompt guidance.

Resemble AI Chatterbox is useful when speech should inherit some direction from an audio prompt while still being controlled by text. It exposes seed, temperature, exaggeration, and guidance weight.

Use it for character-style exploration and expressive reads. If you need a defined preset voice or custom voice selection instead, use Chatterbox Pro.

Model Examples (3)

Example Index01 / 03
Example 01

Gallery guide continuation

Voice-clone continuation from a calm exhibition guide sample.

Open
Source Inputs02
Prompt

On this wall are the lighting references for the storm sequence. Each blue-gray pass was timed to keep the actors readable without losing the feeling of incoming weather.

Audio Prompt
Example input
Parameters04
Prompt
On this wall are the lighting references for the storm sequence. Each blue-gray pass was timed to keep the actors readable without losing the feeling of incoming weather.
Cfg Weight
0.5
Temperature
0.7
Exaggeration
0.45
ttsvoice-clone
Response
Inputs (2)

prompt

String

Text to synthesize

Multi InputMin: 0Max: 100

Audio Prompt

String

Path to the reference audio file (Optional)

Min: 0Max: 100
Parameters (5)

Seed

Number

Seed (0 for random)

Prompt

String

Text to synthesize

Default:

cfg_weight

Number

CFG/Pace weight

Default: 0.5

Temperature

Number

Temperature

Default: 0.8

Exaggeration

Number

Exaggeration (Neutral = 0.5, extreme values can be unstable)

Default: 0.5
Outputs (1)

response

Inferred

response

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Audio / Resemble Ai

Input

TextAudio

Output

Audio

Keywords

Text To SpeechVoice CloningLength Control
Use in Workflow