feat: add audio input support for Gemini translation (#913)

Add input_audio and audio_url content type handlers to
convertOpenAIContentToParts() in geminiHelper.js, converting
OpenAI audio format to Gemini inlineData format.

Also add audio types to VALID_OPENAI_CONTENT_TYPES in
openaiHelper.js so they are not stripped by filterToOpenAIFormat().

Fixes #912

open-sse/translator/helpers/openaiHelper.js

@@ -1,7 +1,7 @@
 // OpenAI helper functions for translator
 
 // Valid OpenAI content block types
-export const VALID_OPENAI_CONTENT_TYPES = ["text", "image_url", "image"];
+export const VALID_OPENAI_CONTENT_TYPES = ["text", "image_url", "image", "input_audio", "audio_url"];
 export const VALID_OPENAI_MESSAGE_TYPES = ["text", "image_url", "image", "tool_calls", "tool_result"];
 
 // Filter messages to OpenAI standard format