ComfyUI Node
Inworld TTS 2 (Replicate)
A ComfyUI node in Replicate Select/tts with 8 inputs and 1 output.
Inworld TTS 2 (Replicate)
- audio
◄text►
◄voice_idAshley►
◄languageauto►
◄temperature0.00►
◄audio_formatmp3►
◄sample_rate48000►
◄speaking_rate0.00►
◄text_normalizationauto►
CategoryReplicate Select/tts
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| text | STRING | The text to convert to speech. Maximum 2,000 characters. Supports natural-language steering with bracketed instructions placed before the text they apply to (e.g. `[say excitedly]`, `[whisper in a hus | |
| voice_idopt | STRING | Ashley | The voice to use. Use a preset voice name (e.g. 'Ashley', 'Dennis', 'Alex', 'Darlene') or a custom cloned voice ID. |
| languageopt | COMBO | auto | Language of the input text. Use 'auto' to let the model detect the language. Supported production languages: English (en), Chinese (zh), Japanese (ja), Korean (ko), Russian (ru), Italian (it), Spanish |
| temperatureopt | FLOAT | 0.000–2 | Controls randomness when generating audio. Higher values produce more expressive results, lower values are more deterministic. Set to 0 to use the model default (1.1). |
| audio_formatopt | COMBO | mp3 | Output audio format. |
| sample_rateopt | COMBO | 48000 | Audio sample rate in Hz. |
| speaking_rateopt | FLOAT | 0.000–1.5 | Speaking speed multiplier. Set to 0 for normal speed (1.0). |
| text_normalizationopt | COMBO | auto | Controls whether numbers, dates, and abbreviations are expanded before synthesis. 'auto' lets the model decide, 'on' always normalizes, 'off' reads text as-is. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| audio | AUDIO | — |