ComfyUI Node

Qwen3-TTS 1.7B Base

A ComfyUI node in Runware/Audio/alibaba with 10 inputs and 1 output.

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

Inputs (10)

NameTypeDefaultDescription
speechRUNWARE_SPEECH
audioSTRINGAudio input (UUID or URL).
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.
settings.transcriptoptSTRINGTranscript of the reference audio. Required for ICL mode, optional for x-vector-only mode.
settings.xVectorOnlyoptBOOLEANfalseIf true, uses speaker embedding only (no transcript needed, lower similarity). If false, uses ICL mode (requires transcript, higher quality).
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