Dify · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Dify Service Audio API

3 actions 3 updates phrasing extends openapi/dify-audio-api-openapi.yml

Generated by API Evangelist Written by API Evangelist tooling for Dify's API. It is a proposal applied on top of the contract, not a document Dify publishes.

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 3

$.info

$.paths['/audio-to-text'].post

$.paths['/text-to-audio'].post

OpenAPI Overlay

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Dify Service Audio API
  version: 1.0.0
extends: openapi/dify-audio-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 2
- target: $.paths['/audio-to-text'].post
  update:
    x-apievangelist-phrasing:
      intent: Transcribe an audio file to text
      effect: write
      questions:
      - How do I turn a voice recording into text with my Dify app?
      - Which audio formats can I upload for speech-to-text transcription?
      instructions:
      - text: Transcribe the audio file {file} to text.
        slots:
          file: requestBody.file
      - text: Convert recording {file} to text for end user {user}.
        slots:
          file: requestBody.file
          user: requestBody.user
      method: generated
      generated: '2026-09-26'
- target: $.paths['/text-to-audio'].post
  update:
    x-apievangelist-phrasing:
      intent: Convert text or a message answer to speech
      effect: write
      questions:
      - Can I have an existing chat answer read aloud as audio?
      - Which voice will text-to-speech use, and can I pick a different one?
      instructions:
      - text: Synthesize speech for the text {text}.
        slots:
          text: requestBody.text
      - text: Voice the answer of message {message_id} as audio using voice {voice}.
        slots:
          message_id: requestBody.message_id
          voice: requestBody.voice
      method: generated
      generated: '2026-09-26'