com.openai.unity 5.2.3 (#132)

- switched audio encoding from wav to ogg
- changed Audio.TranscriptionRequest.Temperature int? -> float?

Documentation~/README.md

@@ -42,6 +42,7 @@ The recommended installation method is though the unity package manager and [Ope
   - [com.utilities.rest](https://github.com/RageAgainstThePixel/com.utilities.rest)
   - [com.utilities.audio](https://github.com/RageAgainstThePixel/com.utilities.audio)
   - [com.utilities.encoder.wav](https://github.com/RageAgainstThePixel/com.utilities.encoder.wav)
+  - [com.utilities.encoder.ogg](https://github.com/RageAgainstThePixel/com.utilities.encoder.ogg)
 
 ---
 

Runtime/Audio/AudioTranscriptionRequest.cs

@@ -3,7 +3,7 @@
 using System;
 using System.IO;
 using UnityEngine;
-using Utilities.Encoding.Wav;
+using Utilities.Encoding.OggVorbis;
 
 namespace OpenAI.Audio
 {
@@ -13,7 +13,7 @@ public sealed class AudioTranscriptionRequest : IDisposable
         /// Constructor.
         /// </summary>
         /// <param name="audioPath">
-        /// The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
+        /// The audio file to transcribe, in one of these formats flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
         /// </param>
         /// <param name="model">
         /// ID of the model to use.
@@ -59,7 +59,7 @@ public AudioTranscriptionRequest(
         /// The <see cref="AudioClip"/> to transcribe.
         /// </param>
         /// <param name="model">
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </param>
         /// <param name="prompt">
         /// Optional, An optional text to guide the model's style or continue a previous audio segment.<br/>
@@ -91,7 +91,7 @@ public AudioTranscriptionRequest(
             AudioResponseFormat responseFormat = AudioResponseFormat.Json,
             float? temperature = null,
             string language = null)
-            : this(new MemoryStream(audio.EncodeToWav()), $"{audio.name}.wav", model, prompt, responseFormat, temperature, language)
+            : this(new MemoryStream(audio.EncodeToOggVorbis()), $"{audio.name}.ogg", model, prompt, responseFormat, temperature, language)
         {
         }
 
@@ -105,7 +105,7 @@ public AudioTranscriptionRequest(
         /// The name of the audio file to transcribe.
         /// </param>
         /// <param name="model">
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </param>
         /// <param name="prompt">
         /// Optional, An optional text to guide the model's style or continue a previous audio segment.<br/>
@@ -157,7 +157,7 @@ public AudioTranscriptionRequest(
         ~AudioTranscriptionRequest() => Dispose(false);
 
         /// <summary>
-        /// The audio file to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
+        /// The audio file to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
         /// </summary>
         public Stream Audio { get; }
 
@@ -167,7 +167,7 @@ public AudioTranscriptionRequest(
         public string AudioName { get; }
 
         /// <summary>
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </summary>
         public string Model { get; }
 

Runtime/Audio/AudioTranslationRequest.cs

@@ -3,7 +3,7 @@
 using System;
 using System.IO;
 using UnityEngine;
-using Utilities.Encoding.Wav;
+using Utilities.Encoding.OggVorbis;
 
 namespace OpenAI.Audio
 {
@@ -13,10 +13,10 @@ public sealed class AudioTranslationRequest : IDisposable
         /// Constructor.
         /// </summary>
         /// <param name="audioPath">
-        /// The audio file to translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm
+        /// The audio file to translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
         /// </param>
         /// <param name="model">
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </param>
         /// <param name="prompt">
         /// Optional, An optional text to guide the model's style or continue a previous audio segment.<br/>
@@ -49,7 +49,7 @@ public AudioTranslationRequest(
         /// The <see cref="AudioClip"/> to translate.
         /// </param>
         /// <param name="model">
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </param>
         /// <param name="prompt">
         /// Optional, An optional text to guide the model's style or continue a previous audio segment.<br/>
@@ -70,16 +70,16 @@ public AudioTranslationRequest(
             string model = null,
             string prompt = null,
             AudioResponseFormat responseFormat = AudioResponseFormat.Json,
-            int? temperature = null)
-            : this(new MemoryStream(audio.EncodeToWav()), $"{audio.name}.wav", model, prompt, responseFormat, temperature)
+            float? temperature = null)
+            : this(new MemoryStream(audio.EncodeToOggVorbis()), $"{audio.name}.ogg", model, prompt, responseFormat, temperature)
         {
         }
 
         /// <summary>
         /// Constructor.
         /// </summary>
         /// <param name="audio">
-        /// The audio file to translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.
+        /// The audio file to translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
         /// </param>
         /// <param name="audioName">
         /// The name of the audio file to translate.
@@ -107,7 +107,7 @@ public AudioTranslationRequest(
             string model = null,
             string prompt = null,
             AudioResponseFormat responseFormat = AudioResponseFormat.Json,
-            int? temperature = null)
+            float? temperature = null)
         {
             Audio = audio;
 
@@ -136,7 +136,7 @@ public AudioTranslationRequest(
         public string AudioName { get; }
 
         /// <summary>
-        /// ID of the model to use. Only whisper-1 is currently available.
+        /// ID of the model to use.
         /// </summary>
         public string Model { get; }
 
@@ -158,7 +158,7 @@ public AudioTranslationRequest(
         /// the model will use log probability to automatically increase the temperature until certain thresholds are hit.<br/>
         /// Defaults to 0
         /// </summary>
-        public int? Temperature { get; }
+        public float? Temperature { get; }
 
         private void Dispose(bool disposing)
         {

Runtime/OpenAI.asmdef

@@ -4,7 +4,8 @@
     "references": [
         "GUID:7958db66189566541a6363568aee1575",
         "GUID:a6609af893242c7438d701ddd4cce46a",
-        "GUID:f7a0d77b5e1d79742a738fb859ee2f28"
+        "GUID:f7a0d77b5e1d79742a738fb859ee2f28",
+        "GUID:fe98ce187c2363b409d00954d687ec68"
     ],
     "includePlatforms": [],
     "excludePlatforms": [],

package.json

@@ -3,7 +3,7 @@
   "displayName": "OpenAI",
   "description": "A OpenAI package for the Unity Game Engine to use GPT-4, GPT-3.5, GPT-3 and Dall-E though their RESTful API (currently in beta).\n\nIndependently developed, this is not an official library and I am not affiliated with OpenAI.\n\nAn OpenAI API account is required.",
   "keywords": [],
-  "version": "5.2.2",
+  "version": "5.2.3",
   "unity": "2021.3",
   "documentationUrl": "https://github.com/RageAgainstThePixel/com.openai.unity#documentation",
   "changelogUrl": "https://github.com/RageAgainstThePixel/com.openai.unity/releases",
@@ -18,7 +18,8 @@
   },
   "dependencies": {
     "com.utilities.rest": "2.2.5",
-    "com.utilities.encoder.wav": "1.0.8"
+    "com.utilities.encoder.wav": "1.0.8",
+    "com.utilities.encoder.ogg": "3.0.12"
   },
   "samples": [
     {