voice-router-dev 0.1.6 → 0.1.8

package/dist/index.d.ts

@@ -40,6 +40,18 @@ type AudioChannels = 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8;
  * Supported transcription providers
  */
 type TranscriptionProvider = "gladia" | "assemblyai" | "deepgram" | "azure-stt" | "openai-whisper" | "speechmatics";
+/**
+ * Providers that support real-time streaming transcription
+ */
+type StreamingProvider = "gladia" | "deepgram" | "assemblyai";
+/**
+ * Providers that only support batch/async transcription
+ */
+type BatchOnlyProvider = "azure-stt" | "openai-whisper" | "speechmatics";
+/**
+ * WebSocket session status for streaming transcription
+ */
+type SessionStatus = "connecting" | "open" | "closing" | "closed";
 /**
  * Provider capabilities - indicates which features each provider supports
  */
@@ -327,6 +339,39 @@ interface StreamingSession {
     createdAt: Date;
 }
 
+/**
+ * Standardized error handling utilities for Voice Router SDK
+ *
+ * Provides consistent error codes, messages, and formatting across all adapters.
+ */
+/**
+ * Standard error codes used across all providers
+ *
+ * These codes provide a consistent error taxonomy regardless of which
+ * provider is being used.
+ */
+declare const ERROR_CODES: {
+    /** Failed to parse API response or WebSocket message */
+    readonly PARSE_ERROR: "PARSE_ERROR";
+    /** WebSocket connection error */
+    readonly WEBSOCKET_ERROR: "WEBSOCKET_ERROR";
+    /** Async transcription job did not complete within timeout */
+    readonly POLLING_TIMEOUT: "POLLING_TIMEOUT";
+    /** Transcription processing failed on provider side */
+    readonly TRANSCRIPTION_ERROR: "TRANSCRIPTION_ERROR";
+    /** Connection attempt timed out */
+    readonly CONNECTION_TIMEOUT: "CONNECTION_TIMEOUT";
+    /** Invalid input provided to API */
+    readonly INVALID_INPUT: "INVALID_INPUT";
+    /** Requested operation not supported by provider */
+    readonly NOT_SUPPORTED: "NOT_SUPPORTED";
+    /** No transcription results available */
+    readonly NO_RESULTS: "NO_RESULTS";
+    /** Unspecified or unknown error */
+    readonly UNKNOWN_ERROR: "UNKNOWN_ERROR";
+};
+type ErrorCode = (typeof ERROR_CODES)[keyof typeof ERROR_CODES];
+
 /**
  * Base adapter interface for transcription providers
  * All provider adapters must implement this interface
@@ -444,18 +489,373 @@ interface TranscriptionAdapter {
 declare abstract class BaseAdapter implements TranscriptionAdapter {
     abstract readonly name: TranscriptionProvider;
     abstract readonly capabilities: ProviderCapabilities;
+    /**
+     * Base URL for provider API (must be defined by subclass)
+     */
+    protected abstract baseUrl: string;
     protected config?: ProviderConfig;
     initialize(config: ProviderConfig): void;
     abstract transcribe(audio: AudioInput, options?: TranscribeOptions): Promise<UnifiedTranscriptResponse>;
     abstract getTranscript(transcriptId: string): Promise<UnifiedTranscriptResponse>;
     /**
-     * Helper method to create error responses
+     * Helper method to create error responses with stack traces
+     *
+     * @param error - Error object or unknown error
+     * @param statusCode - Optional HTTP status code
+     * @param code - Optional error code (defaults to extracted or UNKNOWN_ERROR)
      */
-    protected createErrorResponse(error: Error | unknown, statusCode?: number): UnifiedTranscriptResponse;
+    protected createErrorResponse(error: Error | unknown, statusCode?: number, code?: ErrorCode): UnifiedTranscriptResponse;
     /**
      * Helper method to validate configuration
      */
     protected validateConfig(): void;
+    /**
+     * Build axios config for generated API client functions
+     *
+     * @param authHeaderName - Header name for API key (e.g., "Authorization", "x-gladia-key")
+     * @param authHeaderValue - Optional function to format auth header value (defaults to raw API key)
+     * @returns Axios config object
+     */
+    protected getAxiosConfig(authHeaderName?: string, authHeaderValue?: (apiKey: string) => string): {
+        baseURL: string;
+        timeout: number;
+        headers: Record<string, string>;
+    };
+    /**
+     * Generic polling helper for async transcription jobs
+     *
+     * Polls getTranscript() until job completes or times out.
+     *
+     * @param transcriptId - Job/transcript ID to poll
+     * @param options - Polling configuration
+     * @returns Final transcription result
+     */
+    protected pollForCompletion(transcriptId: string, options?: {
+        maxAttempts?: number;
+        intervalMs?: number;
+    }): Promise<UnifiedTranscriptResponse>;
+}
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * The encoding format of the audio stream. Supported formats:
+- PCM: 8, 16, 24, and 32 bits
+- A-law: 8 bits
+- μ-law: 8 bits
+
+Note: No need to add WAV headers to raw audio as the API supports both formats.
+ */
+type StreamingSupportedEncodingEnum = (typeof StreamingSupportedEncodingEnum)[keyof typeof StreamingSupportedEncodingEnum];
+declare const StreamingSupportedEncodingEnum: {
+    readonly "wav/pcm": "wav/pcm";
+    readonly "wav/alaw": "wav/alaw";
+    readonly "wav/ulaw": "wav/ulaw";
+};
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * The sample rate of the audio stream
+ */
+type StreamingSupportedSampleRateEnum = (typeof StreamingSupportedSampleRateEnum)[keyof typeof StreamingSupportedSampleRateEnum];
+declare const StreamingSupportedSampleRateEnum: {
+    readonly NUMBER_8000: 8000;
+    readonly NUMBER_16000: 16000;
+    readonly NUMBER_32000: 32000;
+    readonly NUMBER_44100: 44100;
+    readonly NUMBER_48000: 48000;
+};
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * The bit depth of the audio stream
+ */
+type StreamingSupportedBitDepthEnum = (typeof StreamingSupportedBitDepthEnum)[keyof typeof StreamingSupportedBitDepthEnum];
+declare const StreamingSupportedBitDepthEnum: {
+    readonly NUMBER_8: 8;
+    readonly NUMBER_16: 16;
+    readonly NUMBER_24: 24;
+    readonly NUMBER_32: 32;
+};
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+/**
+ * Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription language.
+ */
+type TranscriptionLanguageCodeEnum = (typeof TranscriptionLanguageCodeEnum)[keyof typeof TranscriptionLanguageCodeEnum];
+declare const TranscriptionLanguageCodeEnum: {
+    readonly af: "af";
+    readonly am: "am";
+    readonly ar: "ar";
+    readonly as: "as";
+    readonly az: "az";
+    readonly ba: "ba";
+    readonly be: "be";
+    readonly bg: "bg";
+    readonly bn: "bn";
+    readonly bo: "bo";
+    readonly br: "br";
+    readonly bs: "bs";
+    readonly ca: "ca";
+    readonly cs: "cs";
+    readonly cy: "cy";
+    readonly da: "da";
+    readonly de: "de";
+    readonly el: "el";
+    readonly en: "en";
+    readonly es: "es";
+    readonly et: "et";
+    readonly eu: "eu";
+    readonly fa: "fa";
+    readonly fi: "fi";
+    readonly fo: "fo";
+    readonly fr: "fr";
+    readonly gl: "gl";
+    readonly gu: "gu";
+    readonly ha: "ha";
+    readonly haw: "haw";
+    readonly he: "he";
+    readonly hi: "hi";
+    readonly hr: "hr";
+    readonly ht: "ht";
+    readonly hu: "hu";
+    readonly hy: "hy";
+    readonly id: "id";
+    readonly is: "is";
+    readonly it: "it";
+    readonly ja: "ja";
+    readonly jw: "jw";
+    readonly ka: "ka";
+    readonly kk: "kk";
+    readonly km: "km";
+    readonly kn: "kn";
+    readonly ko: "ko";
+    readonly la: "la";
+    readonly lb: "lb";
+    readonly ln: "ln";
+    readonly lo: "lo";
+    readonly lt: "lt";
+    readonly lv: "lv";
+    readonly mg: "mg";
+    readonly mi: "mi";
+    readonly mk: "mk";
+    readonly ml: "ml";
+    readonly mn: "mn";
+    readonly mr: "mr";
+    readonly ms: "ms";
+    readonly mt: "mt";
+    readonly my: "my";
+    readonly ne: "ne";
+    readonly nl: "nl";
+    readonly nn: "nn";
+    readonly no: "no";
+    readonly oc: "oc";
+    readonly pa: "pa";
+    readonly pl: "pl";
+    readonly ps: "ps";
+    readonly pt: "pt";
+    readonly ro: "ro";
+    readonly ru: "ru";
+    readonly sa: "sa";
+    readonly sd: "sd";
+    readonly si: "si";
+    readonly sk: "sk";
+    readonly sl: "sl";
+    readonly sn: "sn";
+    readonly so: "so";
+    readonly sq: "sq";
+    readonly sr: "sr";
+    readonly su: "su";
+    readonly sv: "sv";
+    readonly sw: "sw";
+    readonly ta: "ta";
+    readonly te: "te";
+    readonly tg: "tg";
+    readonly th: "th";
+    readonly tk: "tk";
+    readonly tl: "tl";
+    readonly tr: "tr";
+    readonly tt: "tt";
+    readonly uk: "uk";
+    readonly ur: "ur";
+    readonly uz: "uz";
+    readonly vi: "vi";
+    readonly yi: "yi";
+    readonly yo: "yo";
+    readonly zh: "zh";
+};
+
+/**
+ * Generated by orval v7.9.0 🍺
+ * Do not edit manually.
+ * Gladia Control API
+ * OpenAPI spec version: 1.0
+ */
+
+interface LanguageConfig {
+    /** If one language is set, it will be used for the transcription. Otherwise, language will be auto-detected by the model. */
+    languages?: TranscriptionLanguageCodeEnum[];
+    /** If true, language will be auto-detected on each utterance. Otherwise, language will be auto-detected on first utterance and then used for the rest of the transcription. If one language is set, this option will be ignored. */
+    code_switching?: boolean;
+}
+
+/**
+ * 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
+ */
+/**
+ * ListenV1EncodingParameter type definition
+ */
+/**
+ * ListenV1EncodingParameter type definition
+ */
+/**
+ * ListenV1EncodingParameter type definition
+ */
+/**
+ * ListenV1EncodingParameter type definition
+ */
+type ListenV1EncodingParameter = typeof ListenV1EncodingParameter[keyof typeof ListenV1EncodingParameter];
+declare const ListenV1EncodingParameter: {
+    readonly linear16: "linear16";
+    readonly flac: "flac";
+    readonly mulaw: "mulaw";
+    readonly opus: "opus";
+    readonly speex: "speex";
+    readonly g729: "g729";
+};
+
+/**
+ * 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
+ */
+/**
+ * The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available
+ */
+type ListenV1LanguageParameter = string;
+
+/**
+ * Provider-specific streaming option types using OpenAPI-generated schemas
+ *
+ * These types provide compile-time safety by restricting options to what
+ * each provider actually supports according to their OpenAPI specifications.
+ */
+
+/**
+ * Gladia streaming options (from OpenAPI spec)
+ *
+ * Based on the generated `StreamingRequest` type from Gladia's OpenAPI spec.
+ * All supported encodings, sample rates, and bit depths are from the spec.
+ */
+interface GladiaStreamingOptions {
+    /** Audio encoding format - only Gladia-supported formats */
+    encoding?: StreamingSupportedEncodingEnum;
+    /** Sample rate - only Gladia-supported rates */
+    sampleRate?: StreamingSupportedSampleRateEnum;
+    /** Bit depth - only Gladia-supported depths */
+    bitDepth?: StreamingSupportedBitDepthEnum;
+    /** Number of audio channels (1-8) */
+    channels?: number;
+    /** Endpointing duration in seconds (0.01-10) */
+    endpointing?: number;
+    /** Language configuration */
+    languageConfig?: LanguageConfig;
+    /** Interim/partial results */
+    interimResults?: boolean;
+}
+/**
+ * Deepgram streaming options (from OpenAPI spec)
+ *
+ * Based on the generated `ListenV1MediaTranscribeParams` type from Deepgram's OpenAPI spec.
+ * All supported options come directly from the spec.
+ */
+interface DeepgramStreamingOptions {
+    /** Audio encoding format - only Deepgram-supported formats */
+    encoding?: ListenV1EncodingParameter;
+    /** Sample rate in Hz */
+    sampleRate?: number;
+    /** Language code (BCP-47 format) */
+    language?: ListenV1LanguageParameter;
+    /** Enable speaker diarization */
+    diarization?: boolean;
+    /** Enable language detection */
+    languageDetection?: boolean;
+    /** Enable punctuation */
+    punctuate?: boolean;
+    /** Enable smart formatting */
+    smartFormat?: boolean;
+    /** Enable interim results */
+    interimResults?: boolean;
+    /** Callback URL for webhooks */
+    webhookUrl?: string;
+    /** Custom vocabulary/keywords */
+    keywords?: string | string[];
+    /** Number of audio channels */
+    channels?: number;
+}
+/**
+ * AssemblyAI streaming options
+ *
+ * AssemblyAI's streaming API is simpler - it only requires sample_rate.
+ * Note: AssemblyAI only supports PCM16 encoding for streaming.
+ */
+interface AssemblyAIStreamingOptions {
+    /** Sample rate in Hz (8000 or 16000 recommended) */
+    sampleRate?: 8000 | 16000 | 22050 | 44100 | 48000;
+    /** Enable word-level timestamps */
+    wordTimestamps?: boolean;
+}
+/**
+ * Union of all provider-specific streaming options
+ */
+type ProviderStreamingOptions = ({
+    provider: "gladia";
+} & GladiaStreamingOptions) | ({
+    provider: "deepgram";
+} & DeepgramStreamingOptions) | ({
+    provider: "assemblyai";
+} & AssemblyAIStreamingOptions);
+/**
+ * Type-safe streaming options for a specific provider
+ */
+type StreamingOptionsForProvider<P extends StreamingProvider> = P extends "gladia" ? GladiaStreamingOptions : P extends "deepgram" ? DeepgramStreamingOptions : P extends "assemblyai" ? AssemblyAIStreamingOptions : never;
+/**
+ * Type-safe transcribeStream parameters for a specific provider
+ */
+interface TranscribeStreamParams<P extends StreamingProvider> {
+    /** Streaming options specific to this provider */
+    options?: StreamingOptionsForProvider<P> & {
+        provider: P;
+    };
+    /** Event callbacks */
+    callbacks?: StreamingCallbacks;
 }
 
 /**
@@ -608,41 +1008,79 @@ declare class VoiceRouter {
      */
     getTranscript(transcriptId: string, provider: TranscriptionProvider): Promise<UnifiedTranscriptResponse>;
     /**
-     * Stream audio for real-time transcription
-     * Only works with providers that support streaming
+     * Stream audio for real-time transcription with Gladia
      *
-     * @param options - Streaming options including provider selection
+     * @param options - Gladia-specific streaming options (type-safe from OpenAPI spec)
      * @param callbacks - Event callbacks for transcription results
      * @returns Promise that resolves with a StreamingSession
      *
-     * @example
+     * @example Gladia streaming (type-safe!)
      * ```typescript
-     * import { VoiceRouter } from '@meeting-baas/sdk';
-     *
-     * const router = new VoiceRouter();
-     * router.initialize({
-     *   gladia: { apiKey: process.env.GLADIA_KEY },
-     *   deepgram: { apiKey: process.env.DEEPGRAM_KEY }
+     * const session = await router.transcribeStream({
+     *   provider: 'gladia',
+     *   encoding: 'wav/pcm',  // ✅ Only Gladia encodings allowed
+     *   sampleRate: 16000,    // ✅ Only 8000, 16000, 32000, 44100, 48000
+     *   channels: 1
+     * }, {
+     *   onTranscript: (event) => console.log(event.text),
+     *   onError: (error) => console.error(error)
      * });
+     * ```
+     */
+    transcribeStream(options: GladiaStreamingOptions & {
+        provider: "gladia";
+    }, callbacks?: StreamingCallbacks): Promise<StreamingSession>;
+    /**
+     * Stream audio for real-time transcription with Deepgram
+     *
+     * @param options - Deepgram-specific streaming options (type-safe from OpenAPI spec)
+     * @param callbacks - Event callbacks for transcription results
+     * @returns Promise that resolves with a StreamingSession
      *
+     * @example Deepgram streaming (type-safe!)
+     * ```typescript
      * const session = await router.transcribeStream({
      *   provider: 'deepgram',
-     *   encoding: 'linear16',
+     *   encoding: 'linear16',  // ✅ Only Deepgram encodings allowed
      *   sampleRate: 16000,
-     *   language: 'en'
+     *   language: 'en',
+     *   diarization: true
      * }, {
-     *   onTranscript: (event) => console.log(event.text),
-     *   onError: (error) => console.error(error)
+     *   onTranscript: (event) => console.log(event.text)
      * });
+     * ```
+     */
+    transcribeStream(options: DeepgramStreamingOptions & {
+        provider: "deepgram";
+    }, callbacks?: StreamingCallbacks): Promise<StreamingSession>;
+    /**
+     * Stream audio for real-time transcription with AssemblyAI
      *
-     * // Send audio chunks
-     * await session.sendAudio({ data: audioBuffer });
-     * await session.close();
+     * @param options - AssemblyAI-specific streaming options (type-safe from OpenAPI spec)
+     * @param callbacks - Event callbacks for transcription results
+     * @returns Promise that resolves with a StreamingSession
+     *
+     * @example AssemblyAI streaming (type-safe!)
+     * ```typescript
+     * const session = await router.transcribeStream({
+     *   provider: 'assemblyai',
+     *   sampleRate: 16000  // ✅ Only supported sample rates
+     * }, {
+     *   onTranscript: (event) => console.log(event.text)
+     * });
      * ```
      */
-    transcribeStream(options?: StreamingOptions & {
-        provider?: TranscriptionProvider;
+    transcribeStream(options: AssemblyAIStreamingOptions & {
+        provider: "assemblyai";
     }, callbacks?: StreamingCallbacks): Promise<StreamingSession>;
+    /**
+     * Stream audio for real-time transcription (uses default provider)
+     *
+     * @param options - Generic streaming options
+     * @param callbacks - Event callbacks for transcription results
+     * @returns Promise that resolves with a StreamingSession
+     */
+    transcribeStream(options?: StreamingOptions, callbacks?: StreamingCallbacks): Promise<StreamingSession>;
     /**
      * Delete a transcription
      * Not all providers support this operation
@@ -734,12 +1172,16 @@ declare function createVoiceRouter(config: VoiceRouterConfig, adapters?: Transcr
 declare class GladiaAdapter extends BaseAdapter {
     readonly name: "gladia";
     readonly capabilities: ProviderCapabilities;
-    private baseUrl;
+    protected baseUrl: string;
     /**
      * Get axios config for generated API client functions
-     * Configures headers and base URL
+     * Configures headers and base URL using Gladia's x-gladia-key header
      */
-    private getAxiosConfig;
+    protected getAxiosConfig(): {
+        baseURL: string;
+        timeout: number;
+        headers: Record<string, string>;
+    };
     /**
      * Submit audio for transcription
      *
@@ -831,7 +1273,6 @@ declare class GladiaAdapter extends BaseAdapter {
     /**
      * Poll for transcription completion
      */
-    private pollForCompletion;
     /**
      * Stream audio for real-time transcription
      *
@@ -937,13 +1378,17 @@ declare function createGladiaAdapter(config: ProviderConfig): GladiaAdapter;
 declare class AssemblyAIAdapter extends BaseAdapter {
     readonly name: "assemblyai";
     readonly capabilities: ProviderCapabilities;
-    private baseUrl;
+    protected baseUrl: string;
     private wsBaseUrl;
     /**
      * Get axios config for generated API client functions
-     * Configures headers and base URL
+     * Configures headers and base URL using authorization header
      */
-    private getAxiosConfig;
+    protected getAxiosConfig(): {
+        baseURL: string;
+        timeout: number;
+        headers: Record<string, string>;
+    };
     /**
      * Submit audio for transcription
      *
@@ -1036,10 +1481,6 @@ declare class AssemblyAIAdapter extends BaseAdapter {
      * Extract utterances from AssemblyAI response
      */
     private extractUtterances;
-    /**
-     * Poll for transcription completion
-     */
-    private pollForCompletion;
     /**
      * Stream audio for real-time transcription
      *
@@ -1146,7 +1587,7 @@ declare class DeepgramAdapter extends BaseAdapter {
     readonly name: "deepgram";
     readonly capabilities: ProviderCapabilities;
     private client?;
-    private baseUrl;
+    protected baseUrl: string;
     private wsBaseUrl;
     initialize(config: ProviderConfig): void;
     /**
@@ -1356,12 +1797,20 @@ declare function createDeepgramAdapter(config: ProviderConfig): DeepgramAdapter;
 declare class AzureSTTAdapter extends BaseAdapter {
     readonly name: "azure-stt";
     readonly capabilities: ProviderCapabilities;
-    private client?;
     private region?;
-    private baseUrl?;
+    protected baseUrl: string;
     initialize(config: ProviderConfig & {
         region?: string;
     }): void;
+    /**
+     * Get axios config for generated API client functions
+     * Configures headers and base URL using Azure subscription key
+     */
+    protected getAxiosConfig(): {
+        baseURL: string;
+        timeout: number;
+        headers: Record<string, string>;
+    };
     /**
      * Submit audio for transcription
      *
@@ -1495,9 +1944,16 @@ declare function createAzureSTTAdapter(config: ProviderConfig & {
 declare class OpenAIWhisperAdapter extends BaseAdapter {
     readonly name: "openai-whisper";
     readonly capabilities: ProviderCapabilities;
-    private client?;
-    private baseUrl;
-    initialize(config: ProviderConfig): void;
+    protected baseUrl: string;
+    /**
+     * Get axios config for generated API client functions
+     * Configures headers and base URL using Bearer token authorization
+     */
+    protected getAxiosConfig(): {
+        baseURL: string;
+        timeout: number;
+        headers: Record<string, string>;
+    };
     /**
      * Submit audio for transcription
      *
@@ -1622,7 +2078,7 @@ declare class SpeechmaticsAdapter extends BaseAdapter {
     readonly name: "speechmatics";
     readonly capabilities: ProviderCapabilities;
     private client?;
-    private baseUrl;
+    protected baseUrl: string;
     initialize(config: ProviderConfig): void;
     /**
      * Submit audio for transcription
@@ -3293,118 +3749,6 @@ interface NamedEntityRecognitionResult {
     end: number;
 }
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription language.
- */
-type TranscriptionLanguageCodeEnum = (typeof TranscriptionLanguageCodeEnum)[keyof typeof TranscriptionLanguageCodeEnum];
-declare const TranscriptionLanguageCodeEnum: {
-    readonly af: "af";
-    readonly am: "am";
-    readonly ar: "ar";
-    readonly as: "as";
-    readonly az: "az";
-    readonly ba: "ba";
-    readonly be: "be";
-    readonly bg: "bg";
-    readonly bn: "bn";
-    readonly bo: "bo";
-    readonly br: "br";
-    readonly bs: "bs";
-    readonly ca: "ca";
-    readonly cs: "cs";
-    readonly cy: "cy";
-    readonly da: "da";
-    readonly de: "de";
-    readonly el: "el";
-    readonly en: "en";
-    readonly es: "es";
-    readonly et: "et";
-    readonly eu: "eu";
-    readonly fa: "fa";
-    readonly fi: "fi";
-    readonly fo: "fo";
-    readonly fr: "fr";
-    readonly gl: "gl";
-    readonly gu: "gu";
-    readonly ha: "ha";
-    readonly haw: "haw";
-    readonly he: "he";
-    readonly hi: "hi";
-    readonly hr: "hr";
-    readonly ht: "ht";
-    readonly hu: "hu";
-    readonly hy: "hy";
-    readonly id: "id";
-    readonly is: "is";
-    readonly it: "it";
-    readonly ja: "ja";
-    readonly jw: "jw";
-    readonly ka: "ka";
-    readonly kk: "kk";
-    readonly km: "km";
-    readonly kn: "kn";
-    readonly ko: "ko";
-    readonly la: "la";
-    readonly lb: "lb";
-    readonly ln: "ln";
-    readonly lo: "lo";
-    readonly lt: "lt";
-    readonly lv: "lv";
-    readonly mg: "mg";
-    readonly mi: "mi";
-    readonly mk: "mk";
-    readonly ml: "ml";
-    readonly mn: "mn";
-    readonly mr: "mr";
-    readonly ms: "ms";
-    readonly mt: "mt";
-    readonly my: "my";
-    readonly ne: "ne";
-    readonly nl: "nl";
-    readonly nn: "nn";
-    readonly no: "no";
-    readonly oc: "oc";
-    readonly pa: "pa";
-    readonly pl: "pl";
-    readonly ps: "ps";
-    readonly pt: "pt";
-    readonly ro: "ro";
-    readonly ru: "ru";
-    readonly sa: "sa";
-    readonly sd: "sd";
-    readonly si: "si";
-    readonly sk: "sk";
-    readonly sl: "sl";
-    readonly sn: "sn";
-    readonly so: "so";
-    readonly sq: "sq";
-    readonly sr: "sr";
-    readonly su: "su";
-    readonly sv: "sv";
-    readonly sw: "sw";
-    readonly ta: "ta";
-    readonly te: "te";
-    readonly tg: "tg";
-    readonly th: "th";
-    readonly tk: "tk";
-    readonly tl: "tl";
-    readonly tr: "tr";
-    readonly tt: "tt";
-    readonly uk: "uk";
-    readonly ur: "ur";
-    readonly uz: "uz";
-    readonly vi: "vi";
-    readonly yi: "yi";
-    readonly yo: "yo";
-    readonly zh: "zh";
-};
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -5662,20 +6006,6 @@ type InitTranscriptionRequestCustomMetadata = {
     [key: string]: unknown;
 };
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-
-interface LanguageConfig {
-    /** If one language is set, it will be used for the transcription. Otherwise, language will be auto-detected by the model. */
-    languages?: TranscriptionLanguageCodeEnum[];
-    /** If true, language will be auto-detected on each utterance. Otherwise, language will be auto-detected on first utterance and then used for the rest of the transcription. If one language is set, this option will be ignored. */
-    code_switching?: boolean;
-}
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -6289,44 +6619,6 @@ interface RealtimeProcessingConfig {
     sentiment_analysis?: boolean;
 }
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * The bit depth of the audio stream
- */
-type StreamingSupportedBitDepthEnum = (typeof StreamingSupportedBitDepthEnum)[keyof typeof StreamingSupportedBitDepthEnum];
-declare const StreamingSupportedBitDepthEnum: {
-    readonly NUMBER_8: 8;
-    readonly NUMBER_16: 16;
-    readonly NUMBER_24: 24;
-    readonly NUMBER_32: 32;
-};
-
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * The encoding format of the audio stream. Supported formats:
-- PCM: 8, 16, 24, and 32 bits
-- A-law: 8 bits
-- μ-law: 8 bits
-
-Note: No need to add WAV headers to raw audio as the API supports both formats.
- */
-type StreamingSupportedEncodingEnum = (typeof StreamingSupportedEncodingEnum)[keyof typeof StreamingSupportedEncodingEnum];
-declare const StreamingSupportedEncodingEnum: {
-    readonly "wav/pcm": "wav/pcm";
-    readonly "wav/alaw": "wav/alaw";
-    readonly "wav/ulaw": "wav/ulaw";
-};
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -6341,24 +6633,6 @@ declare const StreamingSupportedModels: {
     readonly "solaria-1": "solaria-1";
 };
 
-/**
- * Generated by orval v7.9.0 🍺
- * Do not edit manually.
- * Gladia Control API
- * OpenAPI spec version: 1.0
- */
-/**
- * The sample rate of the audio stream
- */
-type StreamingSupportedSampleRateEnum = (typeof StreamingSupportedSampleRateEnum)[keyof typeof StreamingSupportedSampleRateEnum];
-declare const StreamingSupportedSampleRateEnum: {
-    readonly NUMBER_8000: 8000;
-    readonly NUMBER_16000: 16000;
-    readonly NUMBER_32000: 32000;
-    readonly NUMBER_44100: 44100;
-    readonly NUMBER_48000: 48000;
-};
-
 /**
  * Generated by orval v7.9.0 🍺
  * Do not edit manually.
@@ -10914,4 +11188,4 @@ 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 index_SentimentAnalysisResult 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, index as AssemblyAITypes, AssemblyAIWebhookHandler, type AudioChunk, type AudioInput, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, DeepgramAdapter, DeepgramWebhookHandler, GladiaAdapter, index$1 as GladiaTypes, GladiaWebhookHandler, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingSession, type TranscribeOptions, 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, AzureSTTAdapter, AzureWebhookHandler, BaseAdapter, BaseWebhookHandler, type BatchOnlyProvider, DeepgramAdapter, type DeepgramStreamingOptions, DeepgramWebhookHandler, GladiaAdapter, type GladiaStreamingOptions, index$1 as GladiaTypes, GladiaWebhookHandler, OpenAIWhisperAdapter, type ProviderCapabilities, type ProviderConfig, type ProviderStreamingOptions, type SessionStatus, type Speaker, SpeechmaticsAdapter, SpeechmaticsWebhookHandler, type StreamEvent, type StreamEventType, type StreamingCallbacks, type StreamingOptions, type StreamingOptionsForProvider, type StreamingProvider, type StreamingSession, 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 };