feat: Add missing TTS models and voices

[netr]

Describe the change
This adds the new OpenAI TTS model, includes a new instructions field, and adds missing speech voices.

Provide OpenAI documentation link
https://platform.openai.com/docs/api-reference/audio

Describe your solution

• Add TTSModelGPT4oMini to SpeechModel type
• Adds missing voices to SpeechVoice type
• Added an optional instructions field to the CreateSpeechRequest object, specific to the gpt-4o-mini-tts model.

Tests
No test changes were required. The SpeechModel and SpeechVoice types were already defined, and the instructions field is omitted when empty.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 98.88%. Comparing base (774fc9d) to head (30e8336).
Report is 91 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master     #958      +/-   ##
==========================================
+ Coverage   98.46%   98.88%   +0.41%     
==========================================
  Files          24       27       +3     
  Lines        1364     1786     +422     
==========================================
+ Hits         1343     1766     +423     
+ Misses         15       14       -1     
  Partials        6        6              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[sashabaranov]

Thank you!