kdeps-tools-transcribe_audio

version: 1.2.0
description: 'Transcribe an audio or video file to text through a Whisper API: openai (default), groq, or local (a self-hosted OpenAI-compatible Whisper server). Supports mp3, mp4, mpeg, mpga, m4a, wav, webm. Returns the transcribed text. For offline transcription with no API key use transcribe_audio_offline.'
parameters:
  file:
    type: string
    description: Absolute path to the audio/video file to transcribe
    required: true
  backend:
    type: string
    description: 'Provider: openai (default), groq, or local'
    enum: [openai, groq, local]
    default: openai
  model:
    type: string
    description: 'Transcription model. Default: whisper-1. Groq: whisper-large-v3.'
    default: whisper-1
  baseURL:
    type: string
    description: 'Overrides the backend''s API base URL (the .../v1 part)'
  language:
    type: string
    description: 'ISO-639-1 code (e.g. en, fr); empty = auto-detect'
  prompt:
    type: string
    description: 'Spelling hints for names and terms'
  responseFormat:
    type: string
    description: 'text (default), json, verbose_json, srt or vtt'
    default: text
  temperature:
    type: string
    description: 'Sampling temperature 0-1'
http:
  env:
    OPENAI: [OPENAI_API_KEY, ""]   # optional: local servers may take it or no key at all
    GROQ: [GROQ_API_KEY, ""]
  method: POST
  url: '{{if .args.baseURL}}{{.args.baseURL}}{{else if eq .args.backend "groq"}}https://api.groq.com/openai/v1{{else if eq .args.backend "local"}}http://localhost:8080/v1{{else}}https://api.openai.com/v1{{end}}/audio/transcriptions'
  headers:
    Authorization: '{{if eq .args.backend "groq"}}{{with .env.GROQ}}Bearer {{.}}{{end}}{{else}}{{with .env.OPENAI}}Bearer {{.}}{{end}}{{end}}'
  files:
    file: "{{.args.file}}"
  form:
    model: "{{.args.model}}"
    response_format: "{{.args.responseFormat}}"
    language: "{{.args.language}}"
    prompt: "{{.args.prompt}}"
    temperature: "{{.args.temperature}}"
  paths: [file]
  timeout: 300s