To run this task you must have the following required information:

> Translation must exist in ui:humor.corporate.draft. ElevenLabs connection required.

If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.

---

You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).

Add all steps to your todo list now and begin executing.

## Steps

1. [Read Translation Draft]: Read the file at `session/translation.json` and analyze its contents (Load the current translation data)

2. Verify the translation JSON exists with the original text and translations. If not found, tell the user to run the translation task first.

3. Prepare two versions of the text for audio:

**Professional version:** The original corporate text, read straight and sincere.
Use a professional, measured voice (Rachel or similar).

**Sarcastic version:** The honest translations strung together as a response.
Use a more casual, knowing voice (Charlotte or similar for British dry wit).

Format each as clean readable text for TTS—no JSON, no formatting marks.


4. [Gather Arguments: Text to Speech] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `textFilePath`: the professional version text (original corporate speak)
- `voiceId`: 21m00Tcm4TlvDq8ikWAM
- `modelId` (default: "eleven_multilingual_v2"): eleven_multilingual_v2
- `outputFormat` (default: "mp3_44100_128"): mp3_44100_128
- `outputDir` (default: "session"): ui:humor.corporate.translations directory path with filename corporate-version.mp3

5. [Run Code: Text to Speech]: Call `run_script` with:

```json
{
  "file": {
    "path": https://sk.ills.app/code/media.audio.tts/preview,
    "args": [
      "textFilePath",
      "voiceId",
      "modelId",
      "outputFormat",
      "outputDir"
    ]
  },
  "packages": null
}
```

6. [Gather Arguments: Text to Speech] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `textFilePath`: the sarcastic version text (honest translations)
- `voiceId`: XB0fDUnXU5powFXDhCwa
- `modelId` (default: "eleven_multilingual_v2"): eleven_multilingual_v2
- `outputFormat` (default: "mp3_44100_128"): mp3_44100_128
- `outputDir` (default: "session"): ui:humor.corporate.translations directory path with filename honest-version.mp3

7. [Run Code: Text to Speech]: Call `run_script` with:

```json
{
  "file": {
    "path": https://sk.ills.app/code/media.audio.tts/preview,
    "args": [
      "textFilePath",
      "voiceId",
      "modelId",
      "outputFormat",
      "outputDir"
    ]
  },
  "packages": null
}
```

8. Update the translation record in `documents/corporate/translations/*` to include:

{
  "audioProPath": "path to professional audio",
  "audioHonestPath": "path to sarcastic audio"
}


9. Present the results:

"🎭 Dual audio ready!

**Professional voice:** [path] — The corporate version, delivered with a straight face
**Honest voice:** [path] — What it actually means, said out loud

Play them back-to-back for maximum effect. Perfect for office presentations about 'communication styles'."