You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/libs/tryAGI.OpenAI/Generated/tryAGI.OpenAI.IRealtimeClient.CreateRealtimeSession.g.cs
+44-31Lines changed: 44 additions & 31 deletions
Original file line number
Diff line number
Diff line change
@@ -29,48 +29,55 @@ public partial interface IRealtimeClient
29
29
/// a usable ephemeral API token that can be used to authenticate browser clients<br/>
30
30
/// for the Realtime API.
31
31
/// </summary>
32
-
/// <param name="audio">
33
-
/// Configuration for input and output audio.
34
-
/// </param>
35
32
/// <param name="clientSecret">
36
-
/// Configuration options for the generated client secret.
33
+
/// Ephemeral key returned by the API.
34
+
/// </param>
35
+
/// <param name="inputAudioFormat">
36
+
/// The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
37
37
/// </param>
38
-
/// <param name="include">
39
-
/// Additional fields to include in server outputs.<br/>
40
-
/// - `item.input_audio_transcription.logprobs`: Include logprobs for input audio transcription.
38
+
/// <param name="inputAudioTranscription">
39
+
/// Configuration for input audio transcription, defaults to off and can be<br/>
40
+
/// set to `null` to turn off once on. Input audio transcription is not native<br/>
41
+
/// to the model, since the model consumes audio directly. Transcription runs<br/>
42
+
/// asynchronously and should be treated as rough guidance<br/>
43
+
/// rather than the representation understood by the model.
41
44
/// </param>
42
45
/// <param name="instructions">
43
46
/// The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior.<br/>
44
47
/// Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session.
45
48
/// </param>
46
-
/// <param name="maxOutputTokens">
49
+
/// <param name="maxResponseOutputTokens">
47
50
/// Maximum number of output tokens for a single assistant response,<br/>
48
51
/// inclusive of tool calls. Provide an integer between 1 and 4096 to<br/>
49
52
/// limit output tokens, or `inf` for the maximum available tokens for a<br/>
50
53
/// given model. Defaults to `inf`.
51
54
/// </param>
52
-
/// <param name="model">
53
-
/// The Realtime model used for this session.
54
-
/// </param>
55
-
/// <param name="outputModalities">
55
+
/// <param name="modalities">
56
56
/// The set of modalities the model can respond with. To disable audio,<br/>
57
57
/// set this to ["text"].
58
58
/// </param>
59
+
/// <param name="outputAudioFormat">
60
+
/// The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.
61
+
/// </param>
59
62
/// <param name="prompt">
60
63
/// Reference to a prompt template and its variables. <br/>
Copy file name to clipboardExpand all lines: src/libs/tryAGI.OpenAI/Generated/tryAGI.OpenAI.IRealtimeClient.CreateRealtimeTranscriptionSession.g.cs
+3-14Lines changed: 3 additions & 14 deletions
Original file line number
Diff line number
Diff line change
@@ -31,7 +31,7 @@ public partial interface IRealtimeClient
31
31
/// </summary>
32
32
/// <param name="include">
33
33
/// The set of items to include in the transcription. Current available items are:<br/>
34
-
/// - `item.input_audio_transcription.logprobs`
34
+
/// `item.input_audio_transcription.logprobs`
35
35
/// </param>
36
36
/// <param name="inputAudioFormat">
37
37
/// The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`.<br/>
@@ -44,29 +44,18 @@ public partial interface IRealtimeClient
44
44
/// Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model.<br/>
45
45
/// Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio.
46
46
/// </param>
47
-
/// <param name="inputAudioTranscription">
48
-
/// Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service.
49
-
/// </param>
50
-
/// <param name="model">
51
-
/// ID of the model to use. The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our open source Whisper V2 model).<br/>
/// Configuration for turn detection. Can be set to `null` to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.
56
50
/// </param>
57
-
/// <param name="type">
58
-
/// The type of session to create. Always `transcription` for transcription sessions.
59
-
/// </param>
60
51
/// <param name="cancellationToken">The token to cancel the operation with</param>
0 commit comments