* feat: Add missing TTS models and voices
* feat: Add new instruction field to create speech request
- From docs: Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd.
* fix: add canary-tts back to SpeechModel
* Added 'wav' and 'pcm' Audio Formats
Added "wav" and "pcm" audio formats as per OpenAI API documentation for createSpeech endpoint.
Ref: https://platform.openai.com/docs/api-reference/audio/createSpeech
Supported formats are mp3, opus, aac, flac, wav, and pcm.
* Removed Extra Newline for Sanity Check
* fix: run goimports to get accepted by the linter