Hedra · Arazzo Workflow

Hedra — Generate text-to-speech audio

Version 1.0.0

Pick a voice, submit a text-to-speech generation, and poll for the audio.

1 workflow 1 source API 1 provider
View Spec View on GitHub CompanyArtificial IntelligenceGenerative AIVideo GenerationImage GenerationAudio GenerationText to SpeechAvatarsMediaMachine LearningArazzoWorkflows

Provider

hedra

Workflows

generateAudio
List voices, submit a text-to-speech generation, poll to completion.
3 steps inputs: api_key, model_slug, text, voice_id outputs: generation_id, url
1
listVoices
list_voices_public_voices_get
List available voices (optional discovery step).
2
submitTTS
generate_asset_public_generations_post
Submit the text-to-speech generation.
3
pollStatus
get_status_public_generations__generation_id__status_get
Poll until the audio generation completes.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Hedra — Generate text-to-speech audio
  version: 1.0.0
  summary: Pick a voice, submit a text-to-speech generation, and poll for the audio.
sourceDescriptions:
- name: hedra
  url: ../openapi/hedra-web-api-openapi-original.json
  type: openapi
workflows:
- workflowId: generateAudio
  summary: List voices, submit a text-to-speech generation, poll to completion.
  inputs:
    type: object
    required: [api_key, voice_id, text]
    properties:
      api_key: { type: string }
      voice_id: { type: string }
      text: { type: string }
      model_slug: { type: string, default: "" }
  steps:
  - stepId: listVoices
    description: List available voices (optional discovery step).
    operationId: list_voices_public_voices_get
    parameters:
    - { name: X-API-Key, in: header, value: $inputs.api_key }
    successCriteria:
    - condition: $statusCode == 200
  - stepId: submitTTS
    description: Submit the text-to-speech generation.
    operationId: generate_asset_public_generations_post
    parameters:
    - { name: X-API-Key, in: header, value: $inputs.api_key }
    requestBody:
      contentType: application/json
      payload:
        type: text_to_speech
        voice_id: $inputs.voice_id
        text: $inputs.text
        model_slug: $inputs.model_slug
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      generation_id: $response.body#/id
  - stepId: pollStatus
    description: Poll until the audio generation completes.
    operationId: get_status_public_generations__generation_id__status_get
    parameters:
    - { name: X-API-Key, in: header, value: $inputs.api_key }
    - { name: generation_id, in: path, value: $steps.submitTTS.outputs.generation_id }
    successCriteria:
    - condition: $statusCode == 200
    - context: $response.body
      condition: $.status == "complete"
      type: jsonpath
    outputs:
      url: $response.body#/url
      download_url: $response.body#/download_url
  outputs:
    generation_id: $steps.submitTTS.outputs.generation_id
    url: $steps.pollStatus.outputs.url