voice-router-dev 0.2.2 → 0.2.4

package/dist/index.d.mts

@@ -4349,11 +4349,45 @@ interface Transcription {
     readonly createdDateTime?: string;
 }
 
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Deepgram API Specification
+ * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
+
+ * OpenAPI spec version: 1.0.0
+ */
+type ListenV1ModelParameter = "nova-3" | "nova-3-general" | "nova-3-medical" | "nova-2" | "nova-2-general" | "nova-2-meeting" | "nova-2-finance" | "nova-2-conversationalai" | "nova-2-voicemail" | "nova-2-video" | "nova-2-medical" | "nova-2-drivethru" | "nova-2-automotive" | "nova" | "nova-general" | "nova-phonecall" | "nova-medical" | "enhanced" | "enhanced-general" | "enhanced-meeting" | "enhanced-phonecall" | "enhanced-finance" | "base" | "meeting" | "phonecall" | "finance" | "conversationalai" | "voicemail" | "video" | string;
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * The model used to process the audio. "solaria-1" is used by default.
+ */
+type StreamingSupportedModels = (typeof StreamingSupportedModels)[keyof typeof StreamingSupportedModels];
+declare const StreamingSupportedModels: {
+    readonly "solaria-1": "solaria-1";
+};
+
 /**
  * Unified types for the Voice Router SDK
  * These types provide a provider-agnostic interface for transcription services
  */
 
+/**
+ * Unified transcription model type with autocomplete for all providers
+ *
+ * Includes all known models from:
+ * - Deepgram: nova-3, nova-2, enhanced, base, whisper, etc.
+ * - Gladia: solaria-1
+ *
+ * Also accepts any string for future/custom models.
+ */
+type TranscriptionModel = ListenV1ModelParameter | StreamingSupportedModels;
 /**
  * Supported transcription providers
  */
@@ -4656,6 +4690,19 @@ interface StreamingOptions extends Omit<TranscribeOptions, "webhookUrl"> {
     endpointing?: number;
     /** Maximum duration without endpointing in seconds */
     maxSilence?: number;
+    /**
+     * Model to use for transcription (provider-specific)
+     *
+     * Type-safe with autocomplete for all known models:
+     * - Deepgram: 'nova-2', 'nova-3', 'base', 'enhanced', 'whisper-large', etc.
+     * - Gladia: 'solaria-1' (default)
+     * - AssemblyAI: Not applicable (uses Universal-2 automatically)
+     *
+     * @example
+     * // Use Nova-2 for better multilingual support
+     * { model: 'nova-2', language: 'fr' }
+     */
+    model?: TranscriptionModel;
 }
 /**
  * Callback functions for streaming events
@@ -5004,16 +5051,6 @@ declare const ListenV1EncodingParameter: {
  */
 type ListenV1LanguageParameter = string;
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Deepgram API Specification
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
-
- * OpenAPI spec version: 1.0.0
- */
-type ListenV1ModelParameter = "nova-3" | "nova-3-general" | "nova-3-medical" | "nova-2" | "nova-2-general" | "nova-2-meeting" | "nova-2-finance" | "nova-2-conversationalai" | "nova-2-voicemail" | "nova-2-video" | "nova-2-medical" | "nova-2-drivethru" | "nova-2-automotive" | "nova" | "nova-general" | "nova-phonecall" | "nova-medical" | "enhanced" | "enhanced-general" | "enhanced-meeting" | "enhanced-phonecall" | "enhanced-finance" | "base" | "meeting" | "phonecall" | "finance" | "conversationalai" | "voicemail" | "video" | string;
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -6740,8 +6777,7 @@ declare abstract class BaseWebhookHandler {
  * Gladia webhook handler
  *
  * Handles webhook callbacks from Gladia API:
- * - transcription.created - Job created and queued
- * - transcription.success - Job completed successfully
+ * - transcription.success - Job completed successfully (includes full transcript)
  * - transcription.error - Job failed with error
  *
  * @example
@@ -6763,13 +6799,26 @@ declare abstract class BaseWebhookHandler {
  *
  * if (event.eventType === 'transcription.completed') {
  *   console.log('Transcript:', event.data?.text);
+ *   console.log('Utterances:', event.data?.utterances);
  * }
  * ```
  */
 declare class GladiaWebhookHandler extends BaseWebhookHandler {
     readonly provider: TranscriptionProvider;
+    /**
+     * Convert Gladia WordDTO to unified Word type
+     */
+    private mapWord;
+    /**
+     * Convert Gladia UtteranceDTO to unified Utterance type
+     */
+    private mapUtterance;
     /**
      * Check if payload matches Gladia webhook format
+     *
+     * Gladia callbacks have the structure:
+     * - { id, event: "transcription.success", payload: TranscriptionResultDTO, custom_metadata? }
+     * - { id, event: "transcription.error", error: ErrorDTO, custom_metadata? }
      */
     matches(payload: unknown, _options?: {
         queryParams?: Record<string, string>;
@@ -9584,20 +9633,6 @@ interface RealtimeProcessingConfig {
     sentiment_analysis?: boolean;
 }
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * The model used to process the audio. "solaria-1" is used by default.
- */
-type StreamingSupportedModels = (typeof StreamingSupportedModels)[keyof typeof StreamingSupportedModels];
-declare const StreamingSupportedModels: {
-    readonly "solaria-1": "solaria-1";
-};
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -12558,4 +12593,4 @@ declare namespace index {
   export { index_AudioIntelligenceModelStatus as AudioIntelligenceModelStatus, type index_AutoHighlightResult as AutoHighlightResult, type index_AutoHighlightsResult as AutoHighlightsResult, type index_BadRequestResponse as BadRequestResponse, type index_CannotAccessUploadedFileResponse as CannotAccessUploadedFileResponse, type index_Chapter as Chapter, type index_ContentSafetyLabel as ContentSafetyLabel, type index_ContentSafetyLabelResult as ContentSafetyLabelResult, type index_ContentSafetyLabelsResult as ContentSafetyLabelsResult, type index_ContentSafetyLabelsResultSeverityScoreSummary as ContentSafetyLabelsResultSeverityScoreSummary, type index_ContentSafetyLabelsResultSummary as ContentSafetyLabelsResultSummary, type index_CreateRealtimeTemporaryTokenParams as CreateRealtimeTemporaryTokenParams, type index_Entity as Entity, index_EntityType as EntityType, type Error$1 as Error, type index_GatewayTimeoutResponse as GatewayTimeoutResponse, type index_GetSubtitlesParams as GetSubtitlesParams, type index_InternalServerErrorResponse as InternalServerErrorResponse, type index_LemurActionItemsParams as LemurActionItemsParams, type index_LemurActionItemsParamsAllOf as LemurActionItemsParamsAllOf, type index_LemurActionItemsResponse as LemurActionItemsResponse, type index_LemurBaseParams as LemurBaseParams, type index_LemurBaseParamsContext as LemurBaseParamsContext, type index_LemurBaseParamsContextOneOf as LemurBaseParamsContextOneOf, type index_LemurBaseParamsFinalModel as LemurBaseParamsFinalModel, type index_LemurBaseResponse as LemurBaseResponse, index_LemurModel as LemurModel, type index_LemurQuestion as LemurQuestion, type index_LemurQuestionAnswer as LemurQuestionAnswer, type index_LemurQuestionAnswerParams as LemurQuestionAnswerParams, type index_LemurQuestionAnswerParamsAllOf as LemurQuestionAnswerParamsAllOf, type index_LemurQuestionAnswerResponse as LemurQuestionAnswerResponse, type index_LemurQuestionAnswerResponseAllOf as LemurQuestionAnswerResponseAllOf, type index_LemurQuestionContext as LemurQuestionContext, type index_LemurQuestionContextOneOf as LemurQuestionContextOneOf, type index_LemurResponse as LemurResponse, type index_LemurStringResponse as LemurStringResponse, type index_LemurStringResponseAllOf as LemurStringResponseAllOf, type index_LemurSummaryParams as LemurSummaryParams, type index_LemurSummaryParamsAllOf as LemurSummaryParamsAllOf, type index_LemurSummaryResponse as LemurSummaryResponse, type index_LemurTaskParams as LemurTaskParams, type index_LemurTaskParamsAllOf as LemurTaskParamsAllOf, type index_LemurTaskResponse as LemurTaskResponse, type index_LemurUsage as LemurUsage, type index_ListTranscriptParams as ListTranscriptParams, type index_ListTranscriptsParams as ListTranscriptsParams, type index_NotFoundResponse as NotFoundResponse, type index_PageDetails as PageDetails, type index_PageDetailsNextUrl as PageDetailsNextUrl, type index_PageDetailsPrevUrl as PageDetailsPrevUrl, type index_ParagraphsResponse as ParagraphsResponse, index_PiiPolicy as PiiPolicy, type index_PurgeLemurRequestDataResponse as PurgeLemurRequestDataResponse, type index_RealtimeTemporaryTokenResponse as RealtimeTemporaryTokenResponse, index_RedactPiiAudioQuality as RedactPiiAudioQuality, type index_RedactedAudioNotification as RedactedAudioNotification, type index_RedactedAudioResponse as RedactedAudioResponse, index_RedactedAudioStatus as RedactedAudioStatus, type index_SentencesResponse as SentencesResponse, index_Sentiment as Sentiment, type SentimentAnalysisResult$1 as SentimentAnalysisResult, type index_SentimentAnalysisResultChannel as SentimentAnalysisResultChannel, type index_SentimentAnalysisResultSpeaker as SentimentAnalysisResultSpeaker, type index_ServiceUnavailableResponse as ServiceUnavailableResponse, type index_SeverityScoreSummary as SeverityScoreSummary, index_SpeechModel as SpeechModel, index_SubstitutionPolicy as SubstitutionPolicy, index_SubtitleFormat as SubtitleFormat, index_SummaryModel as SummaryModel, index_SummaryType as SummaryType, type index_Timestamp as Timestamp, type index_TooManyRequestsResponse as TooManyRequestsResponse, type index_TopicDetectionModelResult as TopicDetectionModelResult, type index_TopicDetectionModelResultSummary as TopicDetectionModelResultSummary, type index_TopicDetectionResult as TopicDetectionResult, type index_TopicDetectionResultLabelsItem as TopicDetectionResultLabelsItem, type index_Transcript as Transcript, type index_TranscriptAudioDuration as TranscriptAudioDuration, type index_TranscriptAudioEndAt as TranscriptAudioEndAt, type index_TranscriptAudioStartFrom as TranscriptAudioStartFrom, type index_TranscriptAutoChapters as TranscriptAutoChapters, type index_TranscriptAutoHighlightsResult as TranscriptAutoHighlightsResult, index_TranscriptBoostParam as TranscriptBoostParam, type index_TranscriptBoostParamProperty as TranscriptBoostParamProperty, type index_TranscriptChapters as TranscriptChapters, type index_TranscriptConfidence as TranscriptConfidence, type index_TranscriptContentSafety as TranscriptContentSafety, type index_TranscriptContentSafetyLabels as TranscriptContentSafetyLabels, type index_TranscriptCustomSpelling as TranscriptCustomSpelling, type index_TranscriptCustomSpellingProperty as TranscriptCustomSpellingProperty, type index_TranscriptCustomTopics as TranscriptCustomTopics, type index_TranscriptDisfluencies as TranscriptDisfluencies, type index_TranscriptEntities as TranscriptEntities, type index_TranscriptEntityDetection as TranscriptEntityDetection, type index_TranscriptFilterProfanity as TranscriptFilterProfanity, type index_TranscriptFormatText as TranscriptFormatText, type index_TranscriptIabCategories as TranscriptIabCategories, type index_TranscriptIabCategoriesResult as TranscriptIabCategoriesResult, index_TranscriptLanguageCode as TranscriptLanguageCode, type index_TranscriptLanguageCodeProperty as TranscriptLanguageCodeProperty, type index_TranscriptLanguageConfidence as TranscriptLanguageConfidence, type index_TranscriptLanguageConfidenceThreshold as TranscriptLanguageConfidenceThreshold, type index_TranscriptLanguageDetection as TranscriptLanguageDetection, type index_TranscriptList as TranscriptList, type index_TranscriptListItem as TranscriptListItem, type index_TranscriptListItemCompleted as TranscriptListItemCompleted, type index_TranscriptListItemError as TranscriptListItemError, type index_TranscriptMultichannel as TranscriptMultichannel, type index_TranscriptOptionalParams as TranscriptOptionalParams, type index_TranscriptOptionalParamsLanguageCode as TranscriptOptionalParamsLanguageCode, type index_TranscriptOptionalParamsLanguageCodeOneOf as TranscriptOptionalParamsLanguageCodeOneOf, type index_TranscriptOptionalParamsRedactPiiSub as TranscriptOptionalParamsRedactPiiSub, type index_TranscriptOptionalParamsSpeakersExpected as TranscriptOptionalParamsSpeakersExpected, type index_TranscriptOptionalParamsSpeechModel as TranscriptOptionalParamsSpeechModel, type index_TranscriptOptionalParamsSpeechThreshold as TranscriptOptionalParamsSpeechThreshold, type index_TranscriptOptionalParamsWebhookAuthHeaderName as TranscriptOptionalParamsWebhookAuthHeaderName, type index_TranscriptOptionalParamsWebhookAuthHeaderValue as TranscriptOptionalParamsWebhookAuthHeaderValue, type index_TranscriptParagraph as TranscriptParagraph, type index_TranscriptParams as TranscriptParams, type index_TranscriptParamsAllOf as TranscriptParamsAllOf, type index_TranscriptPunctuate as TranscriptPunctuate, type index_TranscriptReadyNotification as TranscriptReadyNotification, index_TranscriptReadyStatus as TranscriptReadyStatus, type index_TranscriptRedactPiiAudio as TranscriptRedactPiiAudio, type index_TranscriptRedactPiiAudioQuality as TranscriptRedactPiiAudioQuality, type index_TranscriptRedactPiiPolicies as TranscriptRedactPiiPolicies, type index_TranscriptSentence as TranscriptSentence, type index_TranscriptSentenceChannel as TranscriptSentenceChannel, type index_TranscriptSentenceSpeaker as TranscriptSentenceSpeaker, type index_TranscriptSentimentAnalysis as TranscriptSentimentAnalysis, type index_TranscriptSentimentAnalysisResults as TranscriptSentimentAnalysisResults, type index_TranscriptSpeakerLabels as TranscriptSpeakerLabels, type index_TranscriptSpeakersExpected as TranscriptSpeakersExpected, type index_TranscriptSpeechModel as TranscriptSpeechModel, type index_TranscriptSpeechThreshold as TranscriptSpeechThreshold, type index_TranscriptSpeedBoost as TranscriptSpeedBoost, index_TranscriptStatus as TranscriptStatus, type index_TranscriptSummary as TranscriptSummary, type index_TranscriptSummaryModel as TranscriptSummaryModel, type index_TranscriptSummaryType as TranscriptSummaryType, type index_TranscriptText as TranscriptText, type index_TranscriptThrottled as TranscriptThrottled, type index_TranscriptUtterance as TranscriptUtterance, type index_TranscriptUtteranceChannel as TranscriptUtteranceChannel, type index_TranscriptUtterances as TranscriptUtterances, type index_TranscriptWebhookAuthHeaderName as TranscriptWebhookAuthHeaderName, type index_TranscriptWebhookNotification as TranscriptWebhookNotification, type index_TranscriptWebhookStatusCode as TranscriptWebhookStatusCode, type index_TranscriptWebhookUrl as TranscriptWebhookUrl, type index_TranscriptWord as TranscriptWord, type index_TranscriptWordChannel as TranscriptWordChannel, type index_TranscriptWordSpeaker as TranscriptWordSpeaker, type index_TranscriptWords as TranscriptWords, type index_UnauthorizedResponse as UnauthorizedResponse, type index_UploadedFile as UploadedFile, type index_WordSearchMatch as WordSearchMatch, type index_WordSearchParams as WordSearchParams, type index_WordSearchResponse as WordSearchResponse, type index_WordSearchTimestamp as WordSearchTimestamp };
 }
 
-export { AssemblyAIAdapter, type AssemblyAIStreamingOptions, index as AssemblyAITypes, AssemblyAIWebhookHandler, type AudioChunk, type AudioInput, AudioResponseFormat, AudioTranscriptionModel, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, type BatchOnlyProvider, DeepgramAdapter, type DeepgramStreamingOptions, DeepgramWebhookHandler, GladiaAdapter, type GladiaStreamingOptions, index$1 as GladiaTypes, GladiaWebhookHandler, ListenV1EncodingParameter, type ListenV1LanguageParameter, type ListenV1ModelParameter, type ListenV1VersionParameter, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type ProviderRawResponseMap, type ProviderStreamingOptions, type SessionStatus, SpeakV1ContainerParameter, SpeakV1EncodingParameter, SpeakV1SampleRateParameter, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingOptionsForProvider, type StreamingProvider, type StreamingSession, StreamingSupportedBitDepthEnum, StreamingSupportedEncodingEnum, StreamingSupportedSampleRateEnum, type TranscribeOptions, type TranscribeStreamParams, type TranscriptionAdapter, type TranscriptionProvider, type TranscriptionStatus, type UnifiedTranscriptResponse, type UnifiedWebhookEvent, type Utterance, VoiceRouter, type VoiceRouterConfig, type WebhookEventType, WebhookRouter, type WebhookRouterOptions, type WebhookRouterResult, type WebhookValidation, type WebhookVerificationOptions, type Word, createAssemblyAIAdapter, createAssemblyAIWebhookHandler, createAzureSTTAdapter, createAzureWebhookHandler, createDeepgramAdapter, createDeepgramWebhookHandler, createGladiaAdapter, createGladiaWebhookHandler, createOpenAIWhisperAdapter, createSpeechmaticsAdapter, createVoiceRouter, createWebhookRouter };
+export { AssemblyAIAdapter, type AssemblyAIStreamingOptions, index as AssemblyAITypes, AssemblyAIWebhookHandler, type AudioChunk, type AudioInput, AudioResponseFormat, AudioTranscriptionModel, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, type BatchOnlyProvider, DeepgramAdapter, type DeepgramStreamingOptions, DeepgramWebhookHandler, GladiaAdapter, type GladiaStreamingOptions, index$1 as GladiaTypes, GladiaWebhookHandler, ListenV1EncodingParameter, type ListenV1LanguageParameter, type ListenV1ModelParameter, type ListenV1VersionParameter, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type ProviderRawResponseMap, type ProviderStreamingOptions, type SessionStatus, SpeakV1ContainerParameter, SpeakV1EncodingParameter, SpeakV1SampleRateParameter, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingOptionsForProvider, type StreamingProvider, type StreamingSession, StreamingSupportedBitDepthEnum, StreamingSupportedEncodingEnum, StreamingSupportedSampleRateEnum, type TranscribeOptions, type TranscribeStreamParams, type TranscriptionAdapter, type TranscriptionModel, type TranscriptionProvider, type TranscriptionStatus, type UnifiedTranscriptResponse, type UnifiedWebhookEvent, type Utterance, VoiceRouter, type VoiceRouterConfig, type WebhookEventType, WebhookRouter, type WebhookRouterOptions, type WebhookRouterResult, type WebhookValidation, type WebhookVerificationOptions, type Word, createAssemblyAIAdapter, createAssemblyAIWebhookHandler, createAzureSTTAdapter, createAzureWebhookHandler, createDeepgramAdapter, createDeepgramWebhookHandler, createGladiaAdapter, createGladiaWebhookHandler, createOpenAIWhisperAdapter, createSpeechmaticsAdapter, createVoiceRouter, createWebhookRouter };

package/dist/index.d.ts

@@ -4349,11 +4349,45 @@ interface Transcription {
     readonly createdDateTime?: string;
 }
 
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Deepgram API Specification
+ * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
+
+ * OpenAPI spec version: 1.0.0
+ */
+type ListenV1ModelParameter = "nova-3" | "nova-3-general" | "nova-3-medical" | "nova-2" | "nova-2-general" | "nova-2-meeting" | "nova-2-finance" | "nova-2-conversationalai" | "nova-2-voicemail" | "nova-2-video" | "nova-2-medical" | "nova-2-drivethru" | "nova-2-automotive" | "nova" | "nova-general" | "nova-phonecall" | "nova-medical" | "enhanced" | "enhanced-general" | "enhanced-meeting" | "enhanced-phonecall" | "enhanced-finance" | "base" | "meeting" | "phonecall" | "finance" | "conversationalai" | "voicemail" | "video" | string;
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * The model used to process the audio. "solaria-1" is used by default.
+ */
+type StreamingSupportedModels = (typeof StreamingSupportedModels)[keyof typeof StreamingSupportedModels];
+declare const StreamingSupportedModels: {
+    readonly "solaria-1": "solaria-1";
+};
+
 /**
  * Unified types for the Voice Router SDK
  * These types provide a provider-agnostic interface for transcription services
  */
 
+/**
+ * Unified transcription model type with autocomplete for all providers
+ *
+ * Includes all known models from:
+ * - Deepgram: nova-3, nova-2, enhanced, base, whisper, etc.
+ * - Gladia: solaria-1
+ *
+ * Also accepts any string for future/custom models.
+ */
+type TranscriptionModel = ListenV1ModelParameter | StreamingSupportedModels;
 /**
  * Supported transcription providers
  */
@@ -4656,6 +4690,19 @@ interface StreamingOptions extends Omit<TranscribeOptions, "webhookUrl"> {
     endpointing?: number;
     /** Maximum duration without endpointing in seconds */
     maxSilence?: number;
+    /**
+     * Model to use for transcription (provider-specific)
+     *
+     * Type-safe with autocomplete for all known models:
+     * - Deepgram: 'nova-2', 'nova-3', 'base', 'enhanced', 'whisper-large', etc.
+     * - Gladia: 'solaria-1' (default)
+     * - AssemblyAI: Not applicable (uses Universal-2 automatically)
+     *
+     * @example
+     * // Use Nova-2 for better multilingual support
+     * { model: 'nova-2', language: 'fr' }
+     */
+    model?: TranscriptionModel;
 }
 /**
  * Callback functions for streaming events
@@ -5004,16 +5051,6 @@ declare const ListenV1EncodingParameter: {
  */
 type ListenV1LanguageParameter = string;
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Deepgram API Specification
- * APIs for speech-to-text transcription, text-to-speech synthesis, language understanding, and account management.
-
- * OpenAPI spec version: 1.0.0
- */
-type ListenV1ModelParameter = "nova-3" | "nova-3-general" | "nova-3-medical" | "nova-2" | "nova-2-general" | "nova-2-meeting" | "nova-2-finance" | "nova-2-conversationalai" | "nova-2-voicemail" | "nova-2-video" | "nova-2-medical" | "nova-2-drivethru" | "nova-2-automotive" | "nova" | "nova-general" | "nova-phonecall" | "nova-medical" | "enhanced" | "enhanced-general" | "enhanced-meeting" | "enhanced-phonecall" | "enhanced-finance" | "base" | "meeting" | "phonecall" | "finance" | "conversationalai" | "voicemail" | "video" | string;
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -6740,8 +6777,7 @@ declare abstract class BaseWebhookHandler {
  * Gladia webhook handler
  *
  * Handles webhook callbacks from Gladia API:
- * - transcription.created - Job created and queued
- * - transcription.success - Job completed successfully
+ * - transcription.success - Job completed successfully (includes full transcript)
  * - transcription.error - Job failed with error
  *
  * @example
@@ -6763,13 +6799,26 @@ declare abstract class BaseWebhookHandler {
  *
  * if (event.eventType === 'transcription.completed') {
  *   console.log('Transcript:', event.data?.text);
+ *   console.log('Utterances:', event.data?.utterances);
  * }
  * ```
  */
 declare class GladiaWebhookHandler extends BaseWebhookHandler {
     readonly provider: TranscriptionProvider;
+    /**
+     * Convert Gladia WordDTO to unified Word type
+     */
+    private mapWord;
+    /**
+     * Convert Gladia UtteranceDTO to unified Utterance type
+     */
+    private mapUtterance;
     /**
      * Check if payload matches Gladia webhook format
+     *
+     * Gladia callbacks have the structure:
+     * - { id, event: "transcription.success", payload: TranscriptionResultDTO, custom_metadata? }
+     * - { id, event: "transcription.error", error: ErrorDTO, custom_metadata? }
      */
     matches(payload: unknown, _options?: {
         queryParams?: Record<string, string>;
@@ -9584,20 +9633,6 @@ interface RealtimeProcessingConfig {
     sentiment_analysis?: boolean;
 }
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * The model used to process the audio. "solaria-1" is used by default.
- */
-type StreamingSupportedModels = (typeof StreamingSupportedModels)[keyof typeof StreamingSupportedModels];
-declare const StreamingSupportedModels: {
-    readonly "solaria-1": "solaria-1";
-};
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -12558,4 +12593,4 @@ declare namespace index {
   export { index_AudioIntelligenceModelStatus as AudioIntelligenceModelStatus, type index_AutoHighlightResult as AutoHighlightResult, type index_AutoHighlightsResult as AutoHighlightsResult, type index_BadRequestResponse as BadRequestResponse, type index_CannotAccessUploadedFileResponse as CannotAccessUploadedFileResponse, type index_Chapter as Chapter, type index_ContentSafetyLabel as ContentSafetyLabel, type index_ContentSafetyLabelResult as ContentSafetyLabelResult, type index_ContentSafetyLabelsResult as ContentSafetyLabelsResult, type index_ContentSafetyLabelsResultSeverityScoreSummary as ContentSafetyLabelsResultSeverityScoreSummary, type index_ContentSafetyLabelsResultSummary as ContentSafetyLabelsResultSummary, type index_CreateRealtimeTemporaryTokenParams as CreateRealtimeTemporaryTokenParams, type index_Entity as Entity, index_EntityType as EntityType, type Error$1 as Error, type index_GatewayTimeoutResponse as GatewayTimeoutResponse, type index_GetSubtitlesParams as GetSubtitlesParams, type index_InternalServerErrorResponse as InternalServerErrorResponse, type index_LemurActionItemsParams as LemurActionItemsParams, type index_LemurActionItemsParamsAllOf as LemurActionItemsParamsAllOf, type index_LemurActionItemsResponse as LemurActionItemsResponse, type index_LemurBaseParams as LemurBaseParams, type index_LemurBaseParamsContext as LemurBaseParamsContext, type index_LemurBaseParamsContextOneOf as LemurBaseParamsContextOneOf, type index_LemurBaseParamsFinalModel as LemurBaseParamsFinalModel, type index_LemurBaseResponse as LemurBaseResponse, index_LemurModel as LemurModel, type index_LemurQuestion as LemurQuestion, type index_LemurQuestionAnswer as LemurQuestionAnswer, type index_LemurQuestionAnswerParams as LemurQuestionAnswerParams, type index_LemurQuestionAnswerParamsAllOf as LemurQuestionAnswerParamsAllOf, type index_LemurQuestionAnswerResponse as LemurQuestionAnswerResponse, type index_LemurQuestionAnswerResponseAllOf as LemurQuestionAnswerResponseAllOf, type index_LemurQuestionContext as LemurQuestionContext, type index_LemurQuestionContextOneOf as LemurQuestionContextOneOf, type index_LemurResponse as LemurResponse, type index_LemurStringResponse as LemurStringResponse, type index_LemurStringResponseAllOf as LemurStringResponseAllOf, type index_LemurSummaryParams as LemurSummaryParams, type index_LemurSummaryParamsAllOf as LemurSummaryParamsAllOf, type index_LemurSummaryResponse as LemurSummaryResponse, type index_LemurTaskParams as LemurTaskParams, type index_LemurTaskParamsAllOf as LemurTaskParamsAllOf, type index_LemurTaskResponse as LemurTaskResponse, type index_LemurUsage as LemurUsage, type index_ListTranscriptParams as ListTranscriptParams, type index_ListTranscriptsParams as ListTranscriptsParams, type index_NotFoundResponse as NotFoundResponse, type index_PageDetails as PageDetails, type index_PageDetailsNextUrl as PageDetailsNextUrl, type index_PageDetailsPrevUrl as PageDetailsPrevUrl, type index_ParagraphsResponse as ParagraphsResponse, index_PiiPolicy as PiiPolicy, type index_PurgeLemurRequestDataResponse as PurgeLemurRequestDataResponse, type index_RealtimeTemporaryTokenResponse as RealtimeTemporaryTokenResponse, index_RedactPiiAudioQuality as RedactPiiAudioQuality, type index_RedactedAudioNotification as RedactedAudioNotification, type index_RedactedAudioResponse as RedactedAudioResponse, index_RedactedAudioStatus as RedactedAudioStatus, type index_SentencesResponse as SentencesResponse, index_Sentiment as Sentiment, type SentimentAnalysisResult$1 as SentimentAnalysisResult, type index_SentimentAnalysisResultChannel as SentimentAnalysisResultChannel, type index_SentimentAnalysisResultSpeaker as SentimentAnalysisResultSpeaker, type index_ServiceUnavailableResponse as ServiceUnavailableResponse, type index_SeverityScoreSummary as SeverityScoreSummary, index_SpeechModel as SpeechModel, index_SubstitutionPolicy as SubstitutionPolicy, index_SubtitleFormat as SubtitleFormat, index_SummaryModel as SummaryModel, index_SummaryType as SummaryType, type index_Timestamp as Timestamp, type index_TooManyRequestsResponse as TooManyRequestsResponse, type index_TopicDetectionModelResult as TopicDetectionModelResult, type index_TopicDetectionModelResultSummary as TopicDetectionModelResultSummary, type index_TopicDetectionResult as TopicDetectionResult, type index_TopicDetectionResultLabelsItem as TopicDetectionResultLabelsItem, type index_Transcript as Transcript, type index_TranscriptAudioDuration as TranscriptAudioDuration, type index_TranscriptAudioEndAt as TranscriptAudioEndAt, type index_TranscriptAudioStartFrom as TranscriptAudioStartFrom, type index_TranscriptAutoChapters as TranscriptAutoChapters, type index_TranscriptAutoHighlightsResult as TranscriptAutoHighlightsResult, index_TranscriptBoostParam as TranscriptBoostParam, type index_TranscriptBoostParamProperty as TranscriptBoostParamProperty, type index_TranscriptChapters as TranscriptChapters, type index_TranscriptConfidence as TranscriptConfidence, type index_TranscriptContentSafety as TranscriptContentSafety, type index_TranscriptContentSafetyLabels as TranscriptContentSafetyLabels, type index_TranscriptCustomSpelling as TranscriptCustomSpelling, type index_TranscriptCustomSpellingProperty as TranscriptCustomSpellingProperty, type index_TranscriptCustomTopics as TranscriptCustomTopics, type index_TranscriptDisfluencies as TranscriptDisfluencies, type index_TranscriptEntities as TranscriptEntities, type index_TranscriptEntityDetection as TranscriptEntityDetection, type index_TranscriptFilterProfanity as TranscriptFilterProfanity, type index_TranscriptFormatText as TranscriptFormatText, type index_TranscriptIabCategories as TranscriptIabCategories, type index_TranscriptIabCategoriesResult as TranscriptIabCategoriesResult, index_TranscriptLanguageCode as TranscriptLanguageCode, type index_TranscriptLanguageCodeProperty as TranscriptLanguageCodeProperty, type index_TranscriptLanguageConfidence as TranscriptLanguageConfidence, type index_TranscriptLanguageConfidenceThreshold as TranscriptLanguageConfidenceThreshold, type index_TranscriptLanguageDetection as TranscriptLanguageDetection, type index_TranscriptList as TranscriptList, type index_TranscriptListItem as TranscriptListItem, type index_TranscriptListItemCompleted as TranscriptListItemCompleted, type index_TranscriptListItemError as TranscriptListItemError, type index_TranscriptMultichannel as TranscriptMultichannel, type index_TranscriptOptionalParams as TranscriptOptionalParams, type index_TranscriptOptionalParamsLanguageCode as TranscriptOptionalParamsLanguageCode, type index_TranscriptOptionalParamsLanguageCodeOneOf as TranscriptOptionalParamsLanguageCodeOneOf, type index_TranscriptOptionalParamsRedactPiiSub as TranscriptOptionalParamsRedactPiiSub, type index_TranscriptOptionalParamsSpeakersExpected as TranscriptOptionalParamsSpeakersExpected, type index_TranscriptOptionalParamsSpeechModel as TranscriptOptionalParamsSpeechModel, type index_TranscriptOptionalParamsSpeechThreshold as TranscriptOptionalParamsSpeechThreshold, type index_TranscriptOptionalParamsWebhookAuthHeaderName as TranscriptOptionalParamsWebhookAuthHeaderName, type index_TranscriptOptionalParamsWebhookAuthHeaderValue as TranscriptOptionalParamsWebhookAuthHeaderValue, type index_TranscriptParagraph as TranscriptParagraph, type index_TranscriptParams as TranscriptParams, type index_TranscriptParamsAllOf as TranscriptParamsAllOf, type index_TranscriptPunctuate as TranscriptPunctuate, type index_TranscriptReadyNotification as TranscriptReadyNotification, index_TranscriptReadyStatus as TranscriptReadyStatus, type index_TranscriptRedactPiiAudio as TranscriptRedactPiiAudio, type index_TranscriptRedactPiiAudioQuality as TranscriptRedactPiiAudioQuality, type index_TranscriptRedactPiiPolicies as TranscriptRedactPiiPolicies, type index_TranscriptSentence as TranscriptSentence, type index_TranscriptSentenceChannel as TranscriptSentenceChannel, type index_TranscriptSentenceSpeaker as TranscriptSentenceSpeaker, type index_TranscriptSentimentAnalysis as TranscriptSentimentAnalysis, type index_TranscriptSentimentAnalysisResults as TranscriptSentimentAnalysisResults, type index_TranscriptSpeakerLabels as TranscriptSpeakerLabels, type index_TranscriptSpeakersExpected as TranscriptSpeakersExpected, type index_TranscriptSpeechModel as TranscriptSpeechModel, type index_TranscriptSpeechThreshold as TranscriptSpeechThreshold, type index_TranscriptSpeedBoost as TranscriptSpeedBoost, index_TranscriptStatus as TranscriptStatus, type index_TranscriptSummary as TranscriptSummary, type index_TranscriptSummaryModel as TranscriptSummaryModel, type index_TranscriptSummaryType as TranscriptSummaryType, type index_TranscriptText as TranscriptText, type index_TranscriptThrottled as TranscriptThrottled, type index_TranscriptUtterance as TranscriptUtterance, type index_TranscriptUtteranceChannel as TranscriptUtteranceChannel, type index_TranscriptUtterances as TranscriptUtterances, type index_TranscriptWebhookAuthHeaderName as TranscriptWebhookAuthHeaderName, type index_TranscriptWebhookNotification as TranscriptWebhookNotification, type index_TranscriptWebhookStatusCode as TranscriptWebhookStatusCode, type index_TranscriptWebhookUrl as TranscriptWebhookUrl, type index_TranscriptWord as TranscriptWord, type index_TranscriptWordChannel as TranscriptWordChannel, type index_TranscriptWordSpeaker as TranscriptWordSpeaker, type index_TranscriptWords as TranscriptWords, type index_UnauthorizedResponse as UnauthorizedResponse, type index_UploadedFile as UploadedFile, type index_WordSearchMatch as WordSearchMatch, type index_WordSearchParams as WordSearchParams, type index_WordSearchResponse as WordSearchResponse, type index_WordSearchTimestamp as WordSearchTimestamp };
 }
 
-export { AssemblyAIAdapter, type AssemblyAIStreamingOptions, index as AssemblyAITypes, AssemblyAIWebhookHandler, type AudioChunk, type AudioInput, AudioResponseFormat, AudioTranscriptionModel, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, type BatchOnlyProvider, DeepgramAdapter, type DeepgramStreamingOptions, DeepgramWebhookHandler, GladiaAdapter, type GladiaStreamingOptions, index$1 as GladiaTypes, GladiaWebhookHandler, ListenV1EncodingParameter, type ListenV1LanguageParameter, type ListenV1ModelParameter, type ListenV1VersionParameter, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type ProviderRawResponseMap, type ProviderStreamingOptions, type SessionStatus, SpeakV1ContainerParameter, SpeakV1EncodingParameter, SpeakV1SampleRateParameter, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingOptionsForProvider, type StreamingProvider, type StreamingSession, StreamingSupportedBitDepthEnum, StreamingSupportedEncodingEnum, StreamingSupportedSampleRateEnum, type TranscribeOptions, type TranscribeStreamParams, type TranscriptionAdapter, type TranscriptionProvider, type TranscriptionStatus, type UnifiedTranscriptResponse, type UnifiedWebhookEvent, type Utterance, VoiceRouter, type VoiceRouterConfig, type WebhookEventType, WebhookRouter, type WebhookRouterOptions, type WebhookRouterResult, type WebhookValidation, type WebhookVerificationOptions, type Word, createAssemblyAIAdapter, createAssemblyAIWebhookHandler, createAzureSTTAdapter, createAzureWebhookHandler, createDeepgramAdapter, createDeepgramWebhookHandler, createGladiaAdapter, createGladiaWebhookHandler, createOpenAIWhisperAdapter, createSpeechmaticsAdapter, createVoiceRouter, createWebhookRouter };
+export { AssemblyAIAdapter, type AssemblyAIStreamingOptions, index as AssemblyAITypes, AssemblyAIWebhookHandler, type AudioChunk, type AudioInput, AudioResponseFormat, AudioTranscriptionModel, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, type BatchOnlyProvider, DeepgramAdapter, type DeepgramStreamingOptions, DeepgramWebhookHandler, GladiaAdapter, type GladiaStreamingOptions, index$1 as GladiaTypes, GladiaWebhookHandler, ListenV1EncodingParameter, type ListenV1LanguageParameter, type ListenV1ModelParameter, type ListenV1VersionParameter, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type ProviderRawResponseMap, type ProviderStreamingOptions, type SessionStatus, SpeakV1ContainerParameter, SpeakV1EncodingParameter, SpeakV1SampleRateParameter, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingOptionsForProvider, type StreamingProvider, type StreamingSession, StreamingSupportedBitDepthEnum, StreamingSupportedEncodingEnum, StreamingSupportedSampleRateEnum, type TranscribeOptions, type TranscribeStreamParams, type TranscriptionAdapter, type TranscriptionModel, type TranscriptionProvider, type TranscriptionStatus, type UnifiedTranscriptResponse, type UnifiedWebhookEvent, type Utterance, VoiceRouter, type VoiceRouterConfig, type WebhookEventType, WebhookRouter, type WebhookRouterOptions, type WebhookRouterResult, type WebhookValidation, type WebhookVerificationOptions, type Word, createAssemblyAIAdapter, createAssemblyAIWebhookHandler, createAzureSTTAdapter, createAzureWebhookHandler, createDeepgramAdapter, createDeepgramWebhookHandler, createGladiaAdapter, createGladiaWebhookHandler, createOpenAIWhisperAdapter, createSpeechmaticsAdapter, createVoiceRouter, createWebhookRouter };

package/dist/index.js

@@ -2106,7 +2106,8 @@ var GladiaAdapter = class extends BaseAdapter {
       encoding: options?.encoding ? mapEncodingToProvider(options.encoding, "gladia") : void 0,
       sample_rate: validatedSampleRate,
       channels: options?.channels,
-      endpointing: options?.endpointing
+      endpointing: options?.endpointing,
+      model: options?.model
     };
     if (options?.language) {
       streamingRequest.language_config = {
@@ -3368,6 +3369,7 @@ var DeepgramAdapter = class extends BaseAdapter {
     if (options?.sampleRate) params.append("sample_rate", options.sampleRate.toString());
     if (options?.channels) params.append("channels", options.channels.toString());
     if (options?.language) params.append("language", options.language);
+    if (options?.model) params.append("model", options.model);
     if (options?.languageDetection) params.append("detect_language", "true");
     if (options?.diarization) params.append("diarize", "true");
     if (options?.interimResults) params.append("interim_results", "true");
@@ -4353,15 +4355,46 @@ var GladiaWebhookHandler = class extends BaseWebhookHandler {
     super(...arguments);
     this.provider = "gladia";
   }
+  /**
+   * Convert Gladia WordDTO to unified Word type
+   */
+  mapWord(word) {
+    return {
+      text: word.word,
+      start: word.start,
+      end: word.end,
+      confidence: word.confidence
+    };
+  }
+  /**
+   * Convert Gladia UtteranceDTO to unified Utterance type
+   */
+  mapUtterance(utterance) {
+    return {
+      text: utterance.text,
+      start: utterance.start,
+      end: utterance.end,
+      confidence: utterance.confidence,
+      speaker: utterance.speaker !== void 0 ? String(utterance.speaker) : void 0,
+      words: utterance.words?.map((w) => this.mapWord(w))
+    };
+  }
   /**
    * Check if payload matches Gladia webhook format
+   *
+   * Gladia callbacks have the structure:
+   * - { id, event: "transcription.success", payload: TranscriptionResultDTO, custom_metadata? }
+   * - { id, event: "transcription.error", error: ErrorDTO, custom_metadata? }
    */
   matches(payload, _options) {
     if (!payload || typeof payload !== "object") {
       return false;
     }
     const obj = payload;
-    if (!("event" in obj) || !("payload" in obj)) {
+    if (!("id" in obj) || !("event" in obj)) {
+      return false;
+    }
+    if (typeof obj.id !== "string") {
       return false;
     }
     if (typeof obj.event !== "string") {
@@ -4370,11 +4403,13 @@ var GladiaWebhookHandler = class extends BaseWebhookHandler {
     if (!obj.event.startsWith("transcription.")) {
       return false;
     }
-    if (!obj.payload || typeof obj.payload !== "object") {
+    if (obj.event === "transcription.success" && !("payload" in obj)) {
+      return false;
+    }
+    if (obj.event === "transcription.error" && !("error" in obj)) {
       return false;
     }
-    const payloadObj = obj.payload;
-    return typeof payloadObj.id === "string";
+    return true;
   }
   /**
    * Parse Gladia webhook payload to unified format
@@ -4383,38 +4418,57 @@ var GladiaWebhookHandler = class extends BaseWebhookHandler {
     if (!this.matches(payload)) {
       return this.createErrorEvent(payload, "Invalid Gladia webhook payload");
     }
-    const webhookPayload = payload;
-    const jobId = webhookPayload.payload.id;
-    const event = webhookPayload.event;
-    if (event === "transcription.created") {
-      return {
-        success: true,
-        provider: this.provider,
-        eventType: "transcription.created",
-        data: {
-          id: jobId,
-          status: "queued"
-        },
-        timestamp: (/* @__PURE__ */ new Date()).toISOString(),
-        raw: payload
-      };
-    }
+    const obj = payload;
+    const jobId = obj.id;
+    const event = obj.event;
     if (event === "transcription.success") {
+      const successPayload = payload;
+      const result = successPayload.payload;
+      const transcription = result.transcription;
+      const metadata = result.metadata;
+      const utterances = transcription?.utterances?.map(
+        (u) => this.mapUtterance(u)
+      );
+      const words = transcription?.utterances?.flatMap(
+        (u) => u.words?.map((w) => this.mapWord(w)) ?? []
+      );
+      const speakerIds = /* @__PURE__ */ new Set();
+      transcription?.utterances?.forEach((u) => {
+        if (u.speaker !== void 0) {
+          speakerIds.add(u.speaker);
+        }
+      });
+      const speakers = speakerIds.size > 0 ? Array.from(speakerIds).map((id) => ({ id: String(id) })) : void 0;
+      const summary = result.summarization?.success && result.summarization.results ? result.summarization.results : void 0;
       return {
         success: true,
         provider: this.provider,
         eventType: "transcription.completed",
         data: {
           id: jobId,
-          status: "completed"
-          // Note: Full transcript data needs to be fetched via API
-          // using GladiaAdapter.getTranscript(jobId)
+          status: "completed",
+          text: transcription?.full_transcript,
+          duration: metadata?.audio_duration,
+          language: transcription?.languages?.[0],
+          speakers,
+          words,
+          utterances,
+          summary,
+          metadata: {
+            transcription_time: metadata?.transcription_time,
+            billing_time: metadata?.billing_time,
+            number_of_distinct_channels: metadata?.number_of_distinct_channels,
+            custom_metadata: successPayload.custom_metadata
+          },
+          completedAt: (/* @__PURE__ */ new Date()).toISOString()
         },
         timestamp: (/* @__PURE__ */ new Date()).toISOString(),
         raw: payload
       };
     }
     if (event === "transcription.error") {
+      const errorPayload = payload;
+      const error = errorPayload.error;
       return {
         success: false,
         provider: this.provider,
@@ -4422,7 +4476,11 @@ var GladiaWebhookHandler = class extends BaseWebhookHandler {
         data: {
           id: jobId,
           status: "error",
-          error: "Transcription failed"
+          error: error?.message || "Transcription failed",
+          metadata: {
+            error_code: error?.code,
+            custom_metadata: errorPayload.custom_metadata
+          }
         },
         timestamp: (/* @__PURE__ */ new Date()).toISOString(),
         raw: payload