diff --git a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptOptionalParamsSpeakerOptions.g.cs b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptOptionalParamsSpeakerOptions.g.cs
index 57a11f0..3ec2161 100644
--- a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptOptionalParamsSpeakerOptions.g.cs
+++ b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptOptionalParamsSpeakerOptions.g.cs
@@ -21,6 +21,13 @@ public sealed partial class TranscriptOptionalParamsSpeakerOptions
[global::System.Text.Json.Serialization.JsonPropertyName("max_speakers_expected")]
public int? MaxSpeakersExpected { get; set; }
+ ///
+ /// When `true`, includes a `speaker_confidence` field per word and per utterance in the response. See [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#configuration) for more details.
+ /// Default Value: false
+ ///
+ [global::System.Text.Json.Serialization.JsonPropertyName("include_speaker_confidence")]
+ public bool? IncludeSpeakerConfidence { get; set; }
+
///
/// Additional properties that are not explicitly defined in the schema
///
@@ -37,15 +44,21 @@ public sealed partial class TranscriptOptionalParamsSpeakerOptions
/// <Warning>Setting this parameter too high may hurt model accuracy</Warning>
/// A hard upper limit on the number of speaker labels. If more people speak than this value, the additional speakers are merged into existing labels. Setting it higher than the true number of speakers can cause the model to over-split and return more speakers than are actually present. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.
///
+ ///
+ /// When `true`, includes a `speaker_confidence` field per word and per utterance in the response. See [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#configuration) for more details.
+ /// Default Value: false
+ ///
#if NET7_0_OR_GREATER
[global::System.Diagnostics.CodeAnalysis.SetsRequiredMembers]
#endif
public TranscriptOptionalParamsSpeakerOptions(
int? minSpeakersExpected,
- int? maxSpeakersExpected)
+ int? maxSpeakersExpected,
+ bool? includeSpeakerConfidence)
{
this.MinSpeakersExpected = minSpeakersExpected;
this.MaxSpeakersExpected = maxSpeakersExpected;
+ this.IncludeSpeakerConfidence = includeSpeakerConfidence;
}
///
diff --git a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptUtterance.g.cs b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptUtterance.g.cs
index 423badd..6b08dc1 100644
--- a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptUtterance.g.cs
+++ b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptUtterance.g.cs
@@ -57,6 +57,12 @@ public sealed partial class TranscriptUtterance
[global::System.Text.Json.Serialization.JsonRequired]
public required string Speaker { get; set; }
+ ///
+ /// The confidence score for the speaker label of this utterance, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ ///
+ [global::System.Text.Json.Serialization.JsonPropertyName("speaker_confidence")]
+ public double? SpeakerConfidence { get; set; }
+
///
/// Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "Übersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.
///
@@ -93,6 +99,9 @@ public sealed partial class TranscriptUtterance
///
/// The channel of this utterance. The left and right channels are channels 1 and 2. Additional channels increment the channel number sequentially.
///
+ ///
+ /// The confidence score for the speaker label of this utterance, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ ///
///
/// Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "Übersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.
///
@@ -107,6 +116,7 @@ public TranscriptUtterance(
global::System.Collections.Generic.IList words,
string speaker,
string? channel,
+ double? speakerConfidence,
global::System.Collections.Generic.Dictionary? translatedTexts)
{
this.Confidence = confidence;
@@ -116,6 +126,7 @@ public TranscriptUtterance(
this.Words = words ?? throw new global::System.ArgumentNullException(nameof(words));
this.Channel = channel;
this.Speaker = speaker ?? throw new global::System.ArgumentNullException(nameof(speaker));
+ this.SpeakerConfidence = speakerConfidence;
this.TranslatedTexts = translatedTexts;
}
diff --git a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptWord.g.cs b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptWord.g.cs
index e0a1767..2c43d48 100644
--- a/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptWord.g.cs
+++ b/src/libs/AssemblyAI/Generated/AssemblyAI.Models.TranscriptWord.g.cs
@@ -49,6 +49,12 @@ public sealed partial class TranscriptWord
[global::System.Text.Json.Serialization.JsonPropertyName("speaker")]
public string? Speaker { get; set; }
+ ///
+ /// The confidence score for the speaker label of this word, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ ///
+ [global::System.Text.Json.Serialization.JsonPropertyName("speaker_confidence")]
+ public double? SpeakerConfidence { get; set; }
+
///
/// Additional properties that are not explicitly defined in the schema
///
@@ -76,6 +82,9 @@ public sealed partial class TranscriptWord
///
/// The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null
///
+ ///
+ /// The confidence score for the speaker label of this word, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ ///
#if NET7_0_OR_GREATER
[global::System.Diagnostics.CodeAnalysis.SetsRequiredMembers]
#endif
@@ -85,7 +94,8 @@ public TranscriptWord(
int end,
string text,
string? channel,
- string? speaker)
+ string? speaker,
+ double? speakerConfidence)
{
this.Confidence = confidence;
this.Start = start;
@@ -93,6 +103,7 @@ public TranscriptWord(
this.Text = text ?? throw new global::System.ArgumentNullException(nameof(text));
this.Channel = channel;
this.Speaker = speaker;
+ this.SpeakerConfidence = speakerConfidence;
}
///
diff --git a/src/libs/AssemblyAI/openapi.yaml b/src/libs/AssemblyAI/openapi.yaml
index b101025..db718b5 100644
--- a/src/libs/AssemblyAI/openapi.yaml
+++ b/src/libs/AssemblyAI/openapi.yaml
@@ -1900,6 +1900,11 @@ components:
Setting this parameter too high may hurt model accuracy
A hard upper limit on the number of speaker labels. If more people speak than this value, the additional speakers are merged into existing labels. Setting it higher than the true number of speakers can cause the model to over-split and return more speakers than are actually present. The default depends on audio duration: no limit for 0-2 minutes, 10 for 2-10 minutes, and 30 for 10+ minutes. See [Set a range of possible speakers](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#set-a-range-of-possible-speakers) for more details.
type: integer
+ include_speaker_confidence:
+ x-label: Include speaker confidence
+ description: When `true`, includes a `speaker_confidence` field per word and per utterance in the response. See [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers#configuration) for more details.
+ type: boolean
+ default: false
speakers_expected:
x-label: Speakers expected
@@ -2262,6 +2267,13 @@ components:
x-label: Speaker
description: The speaker of this utterance, where each speaker is assigned a sequential capital letter - e.g. "A" for Speaker A, "B" for Speaker B, etc.
type: string
+ speaker_confidence:
+ x-label: Speaker confidence
+ description: The confidence score for the speaker label of this utterance, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ type: [number, "null"]
+ format: double
+ minimum: 0
+ maximum: 1
translated_texts:
x-label: Translated texts
description: 'Translations keyed by language code (e.g., `{"es": "Texto traducido", "de": "Übersetzter Text"}`). Only present when `match_original_utterance` is enabled with translation.'
@@ -5388,6 +5400,13 @@ components:
x-label: Speaker
description: The speaker of the word if [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) is enabled, else null
type: [string, "null"]
+ speaker_confidence:
+ x-label: Speaker confidence
+ description: The confidence score for the speaker label of this word, between 0 and 1. Only present when `speaker_options.include_speaker_confidence` is `true`.
+ type: [number, "null"]
+ format: double
+ minimum: 0
+ maximum: 1
example:
{
text: "Smoke",