ComfyUI Node

Qwen3-TTS 1.7B VoiceDesign

A ComfyUI node in Runware/Audio/alibaba with 8 inputs and 1 output.

By Runware·Created 2 years ago·Updated about a month ago· 140
Qwen3-TTS 1.7B VoiceDesign
  • speech
  • audioSettings
  • audio
positivePrompt
numberResults1
settings.maxNewTokens2048
ttlfalse
ttl_value60
outputFormatMP3
CategoryRunware/Audio/alibaba

Inputs (8)

NameTypeDefaultDescription
speechRUNWARE_SPEECH
positivePromptSTRINGNatural language voice description. Example: 'A warm, cheerful male voice with moderate pace'.
audioSettingsoptRUNWARE_AUDIOSETTINGS
numberResultsoptINT11–4Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
settings.maxNewTokensoptINT2048Audio output token cap. Higher values allow longer audio but risk hangs.
ttloptBOOLEANfalseEnable to set ttl. Off uses the model's default.
ttl_valueoptINT60Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.
outputFormatoptCOMBOMP3File format for the generated audio.

Outputs (1)

NameTypeDescription
audioAUDIO