Use this when:
- You want to convert text to speech
- You need AI-generated audio narration

Returns:
    JSON response containing task_id and audio data when complete.

Example:
    fish_generate_audio(
        text="Hello, welcome to our service!",
        reference_id="d7900c21663f485ab63ebdb7e5905036"
    )

Provides detailed information on how to use the Fish tools effectively,
including parameters, examples, and best practices.

Returns:
    Complete usage guide for Fish TTS tools.

Returns:
    JSON response from /fish/model/{id}.

Use only reference audio authorized for processing and publication as a
reusable voice. There is no private/unlisted option. For one-shot reference
conditioning without saving a reusable model, use fish_generate_audio.
A successful create returns HTTP 201 and a voice _id; pass that _id as
reference_id to fish_generate_audio. Do not retry an uncertain create blindly.

Use this to check if a task is complete and retrieve the resulting audio URL.

Task states:
- 'pending': Task is queued — keep polling
- 'processing': Task is being processed — keep polling
- 'complete': Task finished successfully
- 'failed': Task failed (check error message)

Returns:
    Task status and result data including audio URL.

Efficiently checks the status of multiple audio generation tasks in a
single request.

Returns:
    Status and result data for all queried tasks.