ComfyUI Node
Chatterbox TTS (Multilingual)
Generate speech from text using Chatterbox Multilingual TTS. Supports 23 languages and optional voice cloning.
Chatterbox TTS (Multilingual)
- reference_audio
- audio
◄textHello, this is a test of the Chatterbox text to speech system.►
◄languageen (English)►
◄exaggeration0.50►
◄cfg_weight0.50►
◄temperature0.80►
◄seed0►
Categoryaudio/tts
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | Hello, this is a test of the Chatterbox text to speech system. | Text to synthesize into speech (max 300 characters) |
| language | COMBO | en (English) | Language for text-to-speech synthesis |
| exaggeration | FLOAT | 0.500.25–2 | Speech expressiveness (0.5=neutral, higher=more expressive, extreme values may be unstable) |
| cfg_weight | FLOAT | 0.500–1 | CFG/Pace weight. Set to 0 for language transfer to reduce accent from reference audio. |
| temperature | FLOAT | 0.800.05–5 | Randomness in generation (higher=more varied) |
| seed | INT | 00–4294967295 | Random seed (0 for random generation) |
| reference_audioopt | AUDIO | Optional reference audio for voice cloning. If not provided, uses default voice. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |