feat: add new provider and options on Voice Talk action

Author: Tr00d

Vonage.Test/Voice/Data/TestTalk-request.json

@@ -6,6 +6,18 @@
     "loop": "2",
     "level": "0",
     "language": "en-US",
-    "style": 0
+    "style": 0,
+    "provider": "ElevenLabs",
+    "providerOptions": {
+      "voice_id": "NFG5qt843uXKj4pFvR7C",
+      "model_id": "eleven_multilingual_v2",
+      "voice_settings": {
+        "stability": 1.5,
+        "use_speaker_boost": true,
+        "similarity_boost": 2.4,
+        "style": 1.4,
+        "speed": 2.5
+      }
+    }
   }
 ]

Vonage.Test/Voice/NccoTests.cs

@@ -207,6 +207,20 @@ public void TestTalk() =>
             Level = "0",
             Language = "en-US",
             Style = 0,
+            Provider = TalkAction.TalkProvider.ElevenLabs,
+            ProviderOptions = new TalkProviderOptions
+            {
+                VoiceId = "NFG5qt843uXKj4pFvR7C",
+                ModelId = "eleven_multilingual_v2",
+                Settings = new TalkProviderSettings
+                {
+                    Speed = (decimal) 2.5,
+                    SimilarityBoost = (decimal) 2.4,
+                    UseSpeakerBoost = true,
+                    Stability = (decimal) 1.5,
+                    Style = (decimal) 1.4,
+                },
+            },
         });
 
     [Fact]

Vonage/Voice/Nccos/TalkAction.cs

@@ -1,36 +1,64 @@
-using Newtonsoft.Json;
+#region
+using System.Runtime.Serialization;
+using Newtonsoft.Json;
+using Newtonsoft.Json.Converters;
+#endregion
 
 namespace Vonage.Voice.Nccos;
 
 public class TalkAction : NccoAction
 {
+    /// <summary>
+    /// </summary>
+    public enum TalkProvider
+    {
+        /// <summary>
+        /// </summary>
+        [EnumMember(Value = "ElevenLabs")] ElevenLabs,
+
+        /// <summary>
+        /// </summary>
+        [EnumMember(Value = "Google")] Google,
+
+        /// <summary>
+        /// </summary>
+        [EnumMember(Value = "Polly")] Polly,
+    }
+
     [JsonProperty("action", Order = 0)] public override ActionType Action => ActionType.Talk;
 
     /// <summary>
-    /// Set to true so this action is terminated when the user presses a button on the keypad. 
-    /// Use this feature to enable users to choose an option without having to listen to the whole message 
-    /// in your Interactive Voice Response (IVR ). If you set bargeIn to true on one more Stream actions then 
-    /// the next non-stream action in the NCCO stack must be an input action. The default value is false.
-    /// Once bargeIn is set to true it will stay true (even if bargeIn: false is set in a following action) 
-    /// until an input action is encountered
+    ///     Set to true so this action is terminated when the user presses a button on the keypad.
+    ///     Use this feature to enable users to choose an option without having to listen to the whole message
+    ///     in your Interactive Voice Response (IVR ). If you set bargeIn to true on one more Stream actions then
+    ///     the next non-stream action in the NCCO stack must be an input action. The default value is false.
+    ///     Once bargeIn is set to true it will stay true (even if bargeIn: false is set in a following action)
+    ///     until an input action is encountered
     /// </summary>
     [JsonProperty("bargeIn", Order = 2)]
     public bool BargeIn { get; set; }
 
     /// <summary>
-    /// The language (<see href="https://tools.ietf.org/html/bcp47">BCP-47</see>format) for the message you are sending. Default: en-US. Possible values are listed in the <see href="https://developer.nexmo.com/voice/voice-api/guides/text-to-speech#supported-languages">Text-To-Speech guide</see>.
+    ///     The language (<see href="https://tools.ietf.org/html/bcp47">BCP-47</see>format) for the message you are sending.
+    ///     Default: en-US. Possible values are listed in the
+    ///     <see href="https://developer.nexmo.com/voice/voice-api/guides/text-to-speech#supported-languages">
+    ///         Text-To-Speech
+    ///         guide
+    ///     </see>
+    ///     .
     /// </summary>
     [JsonProperty("language", Order = 6)]
     public string Language { get; set; }
 
     /// <summary>
-    /// The volume level that the speech is played. This can be any value between -1 to 1 with 0 being the default.
+    ///     The volume level that the speech is played. This can be any value between -1 to 1 with 0 being the default.
     /// </summary>
     [JsonProperty("level", Order = 4)]
     public string Level { get; set; }
 
     /// <summary>
-    /// The number of times text is repeated before the Call is closed. The default value is 1. Set to 0 to loop infinitely.
+    ///     The number of times text is repeated before the Call is closed. The default value is 1. Set to 0 to loop
+    ///     infinitely.
     /// </summary>
     [JsonProperty("loop", Order = 3)]
     public string Loop { get; set; }
@@ -43,17 +71,83 @@ public class TalkAction : NccoAction
     public bool Premium { get; set; }
 
     /// <summary>
-    /// The vocal style (vocal range, tessitura and timbre). Default: 0. Possible values are listed in the <see href="https://developer.nexmo.com/voice/voice-api/guides/text-to-speech#supported-languages">Text-To-Speech guide</see>.
+    ///     The vocal style (vocal range, tessitura and timbre). Default: 0. Possible values are listed in the
+    ///     <see href="https://developer.nexmo.com/voice/voice-api/guides/text-to-speech#supported-languages">
+    ///         Text-To-Speech
+    ///         guide
+    ///     </see>
+    ///     .
     /// </summary>
     [JsonProperty("style", Order = 7)]
     public int? Style { get; set; }
 
     /// <summary>
-    /// A string of up to 1,500 characters (excluding SSML tags) containing the message to be 
-    /// synthesized in the Call or Conversation. A single comma in text adds a short pause to the 
-    /// synthesized speech. To add a longer pause a break tag needs to be used in SSML. 
-    /// To use SSML tags, you must enclose the text in a speak element.
+    ///     A string of up to 1,500 characters (excluding SSML tags) containing the message to be
+    ///     synthesized in the Call or Conversation. A single comma in text adds a short pause to the
+    ///     synthesized speech. To add a longer pause a break tag needs to be used in SSML.
+    ///     To use SSML tags, you must enclose the text in a speak element.
     /// </summary>
     [JsonProperty("text", Order = 1)]
     public string Text { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("provider", Order = 9)]
+    [JsonConverter(typeof(StringEnumConverter))]
+    public TalkProvider? Provider { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("providerOptions", Order = 10)]
+    public TalkProviderOptions? ProviderOptions { get; set; }
+}
+
+/// <summary>
+/// </summary>
+public struct TalkProviderOptions
+{
+    /// <summary>
+    /// </summary>
+    [JsonProperty("voice_id", Order = 0)]
+    public string VoiceId { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("model_id", Order = 1)]
+    public string ModelId { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("voice_settings", Order = 1)]
+    public TalkProviderSettings Settings { get; set; }
+}
+
+/// <summary>
+/// </summary>
+public struct TalkProviderSettings
+{
+    /// <summary>
+    /// </summary>
+    [JsonProperty("stability", Order = 0)]
+    public decimal Stability { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("use_speaker_boost", Order = 1)]
+    public bool UseSpeakerBoost { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("similarity_boost", Order = 2)]
+    public decimal SimilarityBoost { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("style", Order = 3)]
+    public decimal Style { get; set; }
+
+    /// <summary>
+    /// </summary>
+    [JsonProperty("speed", Order = 4)]
+    public decimal Speed { get; set; }
 }