Skip to main content

OPENAI_SPEECH

Generate speech audio using the OpenAI Speech API (or corresponding Hub/Azure variants). Reads text from the default text input and returns an audio blob.

At a glance

  • Category LLM
  • Aliases SERVICE_OPENAI_SPEECH
  • Version: 1.0.6
  • Applications: all
  • Scope: all
  • Default Service: OPENAI_SPEECH

Config Options

NameDescriptionDefaultRequiredResolvedConstraintsConditional Rules
modelModel id to use for TTS (e.g. tts-1)NonefalsefalseNoneNone
voiceVoice id to use for synthesisNonefalsefalseNoneNone
response_formatResponse audio format (e.g. mp3, wav, pcm)NonefalsefalseNoneNone
speedPlayback speed multiplier (e.g. 1.0)NonefalsefalseNoneNone
mime_typeOptional MIME type for the produced blob (e.g. audio/mpeg)NonefalsefalseNoneNone

Inputs

TypeDescriptionDefaultRequiredResolved
textText to synthesize. If omitted, the default text input is used.Nonefalsefalse

Outputs

TypeDescriptionOptional
blobGenerated audio blobfalse

Examples

Synthesize simple text to MP3

- step: OPENAI_SPEECH
model: "tts-1"
voice: "alloy"
response_format: "mp3"

See Also

General Resources: