voice-router-dev 0.5.8 → 0.6.0

package/CHANGELOG.md

@@ -5,10 +5,71 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [0.6.0] - 2026-01-10
+## [0.6.0] - 2026-01-11
 
 ### Added
 
+#### OpenAI Official Spec Integration
+
+OpenAI types now auto-generated from the official [Stainless-hosted OpenAPI spec](https://app.stainless.com/api/spec/documented/openai/openapi.documented.yml):
+
+```typescript
+import { OpenAIModel, OpenAIResponseFormat } from 'voice-router-dev/constants'
+import type {
+  RealtimeSessionCreateRequest,
+  RealtimeTranscriptionSessionCreateRequest,
+  CreateTranscriptionResponseDiarizedJson
+} from 'voice-router-dev'
+
+// All models from official spec
+const model = OpenAIModel["gpt-4o-transcribe-diarize"]
+
+// Response formats including diarization
+const format = OpenAIResponseFormat.diarized_json
+```
+
+**What changed:**
+- **Single source of truth**: Stainless live spec (auto-updated by OpenAI)
+- **54 schemas** generated (up from 15 manual types)
+- **7 endpoints** included: batch audio + realtime streaming
+- **Diarization types** now from official spec (`CreateTranscriptionResponseDiarizedJson`)
+- **Realtime API types**: `RealtimeSessionCreateRequest`, `RealtimeTranscriptionSessionCreateRequest`, `VadConfig`, etc.
+
+**New models in `OpenAIModel`:**
+- `whisper-1` - Open source Whisper V2
+- `gpt-4o-transcribe` - GPT-4o based transcription
+- `gpt-4o-mini-transcribe` - Faster, cost-effective
+- `gpt-4o-mini-transcribe-2025-12-15` - Dated version
+- `gpt-4o-transcribe-diarize` - With speaker diarization
+
+**New response formats in `OpenAIResponseFormat`:**
+- `diarized_json` - JSON with speaker annotations (requires `gpt-4o-transcribe-diarize`)
+
+#### OpenAI Realtime Streaming Types
+
+WebSocket event types for OpenAI Realtime API:
+
+```typescript
+import { OpenAIStreamingTypes } from 'voice-router-dev'
+
+// Session creation
+const session: OpenAIStreamingTypes.RealtimeSessionConfig = {
+  modalities: ['text', 'audio'],
+  voice: 'ash',
+  input_audio_format: 'pcm16',
+  input_audio_transcription: { model: 'whisper-1' },
+  turn_detection: { type: 'server_vad', threshold: 0.6 }
+}
+
+// WebSocket event handling
+type ServerEvent = OpenAIStreamingTypes.RealtimeServerEvent
+type ClientEvent = OpenAIStreamingTypes.RealtimeClientEvent
+```
+
+**Endpoints:**
+- OpenAI: `wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview`
+- Azure OpenAI: `wss://{endpoint}/openai/realtime?deployment={model}&api-version={version}`
+
 #### Soniox Provider (8th Provider)
 
 New adapter for [Soniox](https://soniox.com) speech-to-text with batch and streaming support:
@@ -139,8 +200,28 @@ import { zodToFieldConfigs, SonioxApiZodSchemas } from 'voice-router-dev'
 const transcriptionFields = zodToFieldConfigs(SonioxApiZodSchemas.createTranscriptionBody)
 ```
 
+#### SDK Generation Pipeline Diagram
+
+New auto-generated Mermaid diagram showing the SDK generation flow:
+
+```bash
+pnpm openapi:diagram
+```
+
+Generates `docs/sdk-generation-pipeline.mmd` from codebase analysis:
+- Analyzes `sync-specs.js` for remote/manual spec sources
+- Extracts orval config for API/Zod generation
+- Maps streaming type sync scripts
+- Includes consumer layer (router, webhooks, adapters)
+- Shows public API exports
+
 ### Changed
 
+- **OpenAI spec source**: Now uses Stainless live spec instead of manual `openai-whisper-openapi.yml`
+- **`fix-openai-spec.js`**: Filters full OpenAI API to audio + realtime endpoints only
+- **OpenAI adapter**: Uses `OpenAIModel` constants instead of hardcoded strings
+- **Provider capabilities**: OpenAI now shows `streaming: true` (via Realtime API)
+- **Azure adapter**: Uses generated enums instead of hardcoded strings, removed `any` type casts
 - **Speechmatics adapter** now uses generated enums instead of hardcoded string values
 - **Speechmatics adapter** fixed API structure: `sentiment_analysis_config` and `summarization_config` moved to job level (was incorrectly in `transcription_config`)
 - **Speechmatics adapter** fixed `additional_vocab` format: now uses `{content: string}[]` per spec
@@ -152,8 +233,36 @@ const transcriptionFields = zodToFieldConfigs(SonioxApiZodSchemas.createTranscri
 
 ### Fixed
 
+- OpenAI model values now stay in sync with official spec
+- `OpenAIResponseFormat` now includes `diarized_json` from official spec
+- OpenAI `languageDetection` capability is now `true` (language is optional in request)
+- Azure `languageDetection` capability fixed (was incorrectly `false`)
+- Azure `customVocabulary` capability fixed
+- AssemblyAI/Speechmatics streaming types now survive `openapi:clean` (stored in `specs/`)
 - Speechmatics batch field configs now work (was returning empty array)
 - Speechmatics webhook handler now uses generated `RetrieveTranscriptResponse` type
+- **AssemblyAI streaming field configs** now include SDK v3 fields (`keyterms`, `keytermsPrompt`, `speechModel`, `languageDetection`, etc.) - sync script parses both AsyncAPI spec and SDK TypeScript types
+
+#### Soniox Regional Endpoints (Sovereign Cloud)
+
+Regional endpoint support for Soniox data residency:
+
+```typescript
+import { createSonioxAdapter, SonioxRegion } from 'voice-router-dev'
+
+const adapter = createSonioxAdapter({
+  apiKey: process.env.SONIOX_EU_API_KEY,
+  region: SonioxRegion.eu  // EU data residency
+})
+```
+
+| Region | REST API | WebSocket |
+|--------|----------|-----------|
+| `us` (default) | `api.soniox.com` | `stt-rt.soniox.com` |
+| `eu` | `api.eu.soniox.com` | `stt-rt.eu.soniox.com` |
+| `jp` | `api.jp.soniox.com` | `stt-rt.jp.soniox.com` |
+
+**Note:** Soniox API keys are region-specific. Each project is created with a specific region, and the API key only works with that region's endpoint.
 
 ---
 

package/README.md

@@ -1,6 +1,6 @@
 # Voice Router SDK
 
-> Universal speech-to-text router for 6+ transcription providers with a single, unified API.
+> Universal speech-to-text router for 8 transcription providers with a single, unified API.
 
 [![npm version](https://badge.fury.io/js/voice-router-dev.svg)](https://www.npmjs.com/package/voice-router-dev)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
@@ -8,7 +8,7 @@
 
 ## Why Voice Router?
 
-Switch between speech-to-text providers **without changing your code**. One API for Gladia, AssemblyAI, Deepgram, Azure, OpenAI Whisper, and Speechmatics.
+Switch between speech-to-text providers **without changing your code**. One API for Gladia, AssemblyAI, Deepgram, Azure, OpenAI Whisper, Speechmatics, and Soniox.
 
 ```typescript
 import { VoiceRouter } from 'voice-router-dev';
@@ -31,7 +31,7 @@ const result = await router.transcribe(audio, {
 - **Provider-Agnostic** - Switch providers with one line
 - **Unified API** - Same interface for all providers
 - **Webhook Normalization** - Auto-detect and parse webhooks
-- **Real-time Streaming** - WebSocket support (Gladia, AssemblyAI, Deepgram)
+- **Real-time Streaming** - WebSocket support (Gladia, AssemblyAI, Deepgram, Soniox, OpenAI Realtime)
 - **Advanced Features** - Diarization, sentiment, summarization, chapters, entities
 - **Type-Safe** - Full TypeScript support with OpenAPI-generated types
 - **Typed Extended Data** - Access provider-specific features with full autocomplete
@@ -46,8 +46,9 @@ const result = await router.transcribe(audio, {
 | **AssemblyAI** | Yes | Real-time | HMAC | Chapters, entities, content moderation |
 | **Deepgram** | Sync | WebSocket | Yes | PII redaction, keyword boosting |
 | **Azure STT** | Async | No | HMAC | Custom models, language ID |
-| **OpenAI Whisper** | Sync | No | No | gpt-4o, diarization |
+| **OpenAI** | Sync | Realtime | No | gpt-4o, diarization, Realtime API |
 | **Speechmatics** | Async | No | Query params | High accuracy, summarization |
+| **Soniox** | Yes | WebSocket | No | 60+ languages, translation, regions |
 
 ## Installation
 
@@ -371,8 +372,9 @@ Provider-specific implementations:
 - `AssemblyAIAdapter` - AssemblyAI transcription
 - `DeepgramAdapter` - Deepgram transcription
 - `AzureSTTAdapter` - Azure Speech-to-Text
-- `OpenAIWhisperAdapter` - OpenAI Whisper
+- `OpenAIWhisperAdapter` - OpenAI Whisper + Realtime API
 - `SpeechmaticsAdapter` - Speechmatics transcription
+- `SonioxAdapter` - Soniox transcription (batch + streaming)
 
 ## TypeScript Support
 
@@ -651,6 +653,23 @@ router.registerAdapter(new SpeechmaticsAdapter());
 
 Get your API key: https://speechmatics.com
 
+### Soniox
+```typescript
+import { VoiceRouter, SonioxAdapter, SonioxRegion } from 'voice-router-dev';
+
+const router = new VoiceRouter({
+  providers: {
+    soniox: {
+      apiKey: 'YOUR_KEY',
+      region: SonioxRegion.us  // or 'eu', 'jp'
+    }
+  }
+});
+router.registerAdapter(new SonioxAdapter());
+```
+
+Get your API key: https://soniox.com
+
 ## Contributing
 
 Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).

package/dist/constants.d.mts

@@ -736,10 +736,46 @@ declare const DeepgramRegion: {
     /** European Union endpoint */
     readonly eu: "eu";
 };
+/**
+ * Soniox regional endpoints (Sovereign Cloud)
+ *
+ * Soniox offers regional endpoints for data residency compliance.
+ * All audio, transcripts, and logs stay fully in-region.
+ *
+ * | Region | REST API | WebSocket (Real-time) |
+ * |--------|----------|----------------------|
+ * | US (default) | api.soniox.com | stt-rt.soniox.com |
+ * | EU | api.eu.soniox.com | stt-rt.eu.soniox.com |
+ * | Japan | api.jp.soniox.com | stt-rt.jp.soniox.com |
+ *
+ * **Coming soon:** Korea, Australia, India, Canada, Saudi Arabia, UK, Brazil
+ *
+ * @example
+ * ```typescript
+ * import { SonioxRegion } from 'voice-router-dev/constants'
+ *
+ * const adapter = createSonioxAdapter({
+ *   apiKey: process.env.SONIOX_API_KEY,
+ *   region: SonioxRegion.eu
+ * })
+ * ```
+ *
+ * @see https://soniox.com/docs/stt/data-residency - Official data residency docs
+ */
+declare const SonioxRegion: {
+    /** United States (default) */
+    readonly us: "us";
+    /** European Union */
+    readonly eu: "eu";
+    /** Japan */
+    readonly jp: "jp";
+};
 /** Speechmatics region type derived from const object */
 type SpeechmaticsRegionType = (typeof SpeechmaticsRegion)[keyof typeof SpeechmaticsRegion];
 /** Deepgram region type derived from const object */
 type DeepgramRegionType = (typeof DeepgramRegion)[keyof typeof DeepgramRegion];
+/** Soniox region type derived from const object */
+type SonioxRegionType = (typeof SonioxRegion)[keyof typeof SonioxRegion];
 /**
  * Deepgram TTS voice models
  *
@@ -890,7 +926,12 @@ type DeepgramTTSSampleRateType = (typeof DeepgramTTSSampleRate)[keyof typeof Dee
 /**
  * OpenAI Whisper transcription models
  *
- * Values: `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe-diarize`
+ * Values from official spec (auto-synced from Stainless):
+ * - `whisper-1`: Open source Whisper V2 model
+ * - `gpt-4o-transcribe`: GPT-4o based transcription (more accurate)
+ * - `gpt-4o-mini-transcribe`: Faster, cost-effective GPT-4o mini
+ * - `gpt-4o-mini-transcribe-2025-12-15`: Dated version of GPT-4o mini
+ * - `gpt-4o-transcribe-diarize`: GPT-4o with speaker diarization
  *
  * @example
  * ```typescript
@@ -898,28 +939,36 @@ type DeepgramTTSSampleRateType = (typeof DeepgramTTSSampleRate)[keyof typeof Dee
  *
  * { model: OpenAIModel["whisper-1"] }
  * { model: OpenAIModel["gpt-4o-transcribe"] }
+ * { model: OpenAIModel["gpt-4o-transcribe-diarize"] }
  * ```
  */
 declare const OpenAIModel: {
     readonly "whisper-1": "whisper-1";
-    readonly "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe";
     readonly "gpt-4o-transcribe": "gpt-4o-transcribe";
+    readonly "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe";
+    readonly "gpt-4o-mini-transcribe-2025-12-15": "gpt-4o-mini-transcribe-2025-12-15";
     readonly "gpt-4o-transcribe-diarize": "gpt-4o-transcribe-diarize";
 };
 /**
  * OpenAI transcription response formats
  *
- * Values: `json`, `text`, `srt`, `verbose_json`, `vtt`, `diarized_json`
+ * Values from official spec (auto-synced from Stainless):
+ * - `json`: Basic JSON response
+ * - `text`: Plain text
+ * - `srt`: SRT subtitle format
+ * - `verbose_json`: Detailed JSON with timestamps
+ * - `vtt`: VTT subtitle format
+ * - `diarized_json`: JSON with speaker annotations (gpt-4o-transcribe-diarize only)
  *
- * Note: `diarized_json` is only available with `gpt-4o-transcribe-diarize` model.
- * GPT-4o transcribe models only support `json` format.
+ * Note: GPT-4o transcribe models only support `json` format.
+ * For diarization, use `diarized_json` with `gpt-4o-transcribe-diarize` model.
  *
  * @example
  * ```typescript
  * import { OpenAIResponseFormat } from 'voice-router-dev/constants'
  *
  * { responseFormat: OpenAIResponseFormat.verbose_json }
- * { responseFormat: OpenAIResponseFormat.srt }
+ * { responseFormat: OpenAIResponseFormat.diarized_json }
  * ```
  */
 declare const OpenAIResponseFormat: {
@@ -935,4 +984,4 @@ type OpenAIModelType = (typeof OpenAIModel)[keyof typeof OpenAIModel];
 /** OpenAI response format type derived from const object */
 type OpenAIResponseFormatType = (typeof OpenAIResponseFormat)[keyof typeof OpenAIResponseFormat];
 
-export { AssemblyAIEncoding, type AssemblyAIEncodingType, AssemblyAISampleRate, type AssemblyAISampleRateType, AssemblyAISpeechModel, type AssemblyAISpeechModelType, AssemblyAIStatus, type AssemblyAIStatusType, AzureStatus, type AzureStatusType, DeepgramCallbackMethod, type DeepgramCallbackMethodType, DeepgramEncoding, type DeepgramEncodingType, DeepgramIntentMode, type DeepgramIntentModeType, DeepgramModel, type DeepgramModelType, DeepgramRedact, type DeepgramRedactType, DeepgramRegion, type DeepgramRegionType, DeepgramSampleRate, type DeepgramSampleRateType, DeepgramStatus, type DeepgramStatusType, DeepgramTTSContainer, type DeepgramTTSContainerType, DeepgramTTSEncoding, type DeepgramTTSEncodingType, DeepgramTTSModel, type DeepgramTTSModelType, DeepgramTTSSampleRate, type DeepgramTTSSampleRateType, DeepgramTopicMode, type DeepgramTopicModeType, GladiaBitDepth, type GladiaBitDepthType, GladiaEncoding, type GladiaEncodingType, GladiaLanguage, type GladiaLanguageType, GladiaModel, type GladiaModelType, GladiaRegion, type GladiaRegionType, GladiaSampleRate, type GladiaSampleRateType, GladiaStatus, type GladiaStatusType, GladiaTranslationLanguage, type GladiaTranslationLanguageType, OpenAIModel, type OpenAIModelType, OpenAIResponseFormat, type OpenAIResponseFormatType, SpeechmaticsRegion, type SpeechmaticsRegionType };
+export { AssemblyAIEncoding, type AssemblyAIEncodingType, AssemblyAISampleRate, type AssemblyAISampleRateType, AssemblyAISpeechModel, type AssemblyAISpeechModelType, AssemblyAIStatus, type AssemblyAIStatusType, AzureStatus, type AzureStatusType, DeepgramCallbackMethod, type DeepgramCallbackMethodType, DeepgramEncoding, type DeepgramEncodingType, DeepgramIntentMode, type DeepgramIntentModeType, DeepgramModel, type DeepgramModelType, DeepgramRedact, type DeepgramRedactType, DeepgramRegion, type DeepgramRegionType, DeepgramSampleRate, type DeepgramSampleRateType, DeepgramStatus, type DeepgramStatusType, DeepgramTTSContainer, type DeepgramTTSContainerType, DeepgramTTSEncoding, type DeepgramTTSEncodingType, DeepgramTTSModel, type DeepgramTTSModelType, DeepgramTTSSampleRate, type DeepgramTTSSampleRateType, DeepgramTopicMode, type DeepgramTopicModeType, GladiaBitDepth, type GladiaBitDepthType, GladiaEncoding, type GladiaEncodingType, GladiaLanguage, type GladiaLanguageType, GladiaModel, type GladiaModelType, GladiaRegion, type GladiaRegionType, GladiaSampleRate, type GladiaSampleRateType, GladiaStatus, type GladiaStatusType, GladiaTranslationLanguage, type GladiaTranslationLanguageType, OpenAIModel, type OpenAIModelType, OpenAIResponseFormat, type OpenAIResponseFormatType, SonioxRegion, type SonioxRegionType, SpeechmaticsRegion, type SpeechmaticsRegionType };

package/dist/constants.d.ts

@@ -736,10 +736,46 @@ declare const DeepgramRegion: {
     /** European Union endpoint */
     readonly eu: "eu";
 };
+/**
+ * Soniox regional endpoints (Sovereign Cloud)
+ *
+ * Soniox offers regional endpoints for data residency compliance.
+ * All audio, transcripts, and logs stay fully in-region.
+ *
+ * | Region | REST API | WebSocket (Real-time) |
+ * |--------|----------|----------------------|
+ * | US (default) | api.soniox.com | stt-rt.soniox.com |
+ * | EU | api.eu.soniox.com | stt-rt.eu.soniox.com |
+ * | Japan | api.jp.soniox.com | stt-rt.jp.soniox.com |
+ *
+ * **Coming soon:** Korea, Australia, India, Canada, Saudi Arabia, UK, Brazil
+ *
+ * @example
+ * ```typescript
+ * import { SonioxRegion } from 'voice-router-dev/constants'
+ *
+ * const adapter = createSonioxAdapter({
+ *   apiKey: process.env.SONIOX_API_KEY,
+ *   region: SonioxRegion.eu
+ * })
+ * ```
+ *
+ * @see https://soniox.com/docs/stt/data-residency - Official data residency docs
+ */
+declare const SonioxRegion: {
+    /** United States (default) */
+    readonly us: "us";
+    /** European Union */
+    readonly eu: "eu";
+    /** Japan */
+    readonly jp: "jp";
+};
 /** Speechmatics region type derived from const object */
 type SpeechmaticsRegionType = (typeof SpeechmaticsRegion)[keyof typeof SpeechmaticsRegion];
 /** Deepgram region type derived from const object */
 type DeepgramRegionType = (typeof DeepgramRegion)[keyof typeof DeepgramRegion];
+/** Soniox region type derived from const object */
+type SonioxRegionType = (typeof SonioxRegion)[keyof typeof SonioxRegion];
 /**
  * Deepgram TTS voice models
  *
@@ -890,7 +926,12 @@ type DeepgramTTSSampleRateType = (typeof DeepgramTTSSampleRate)[keyof typeof Dee
 /**
  * OpenAI Whisper transcription models
  *
- * Values: `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-4o-transcribe-diarize`
+ * Values from official spec (auto-synced from Stainless):
+ * - `whisper-1`: Open source Whisper V2 model
+ * - `gpt-4o-transcribe`: GPT-4o based transcription (more accurate)
+ * - `gpt-4o-mini-transcribe`: Faster, cost-effective GPT-4o mini
+ * - `gpt-4o-mini-transcribe-2025-12-15`: Dated version of GPT-4o mini
+ * - `gpt-4o-transcribe-diarize`: GPT-4o with speaker diarization
  *
  * @example
  * ```typescript
@@ -898,28 +939,36 @@ type DeepgramTTSSampleRateType = (typeof DeepgramTTSSampleRate)[keyof typeof Dee
  *
  * { model: OpenAIModel["whisper-1"] }
  * { model: OpenAIModel["gpt-4o-transcribe"] }
+ * { model: OpenAIModel["gpt-4o-transcribe-diarize"] }
  * ```
  */
 declare const OpenAIModel: {
     readonly "whisper-1": "whisper-1";
-    readonly "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe";
     readonly "gpt-4o-transcribe": "gpt-4o-transcribe";
+    readonly "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe";
+    readonly "gpt-4o-mini-transcribe-2025-12-15": "gpt-4o-mini-transcribe-2025-12-15";
     readonly "gpt-4o-transcribe-diarize": "gpt-4o-transcribe-diarize";
 };
 /**
  * OpenAI transcription response formats
  *
- * Values: `json`, `text`, `srt`, `verbose_json`, `vtt`, `diarized_json`
+ * Values from official spec (auto-synced from Stainless):
+ * - `json`: Basic JSON response
+ * - `text`: Plain text
+ * - `srt`: SRT subtitle format
+ * - `verbose_json`: Detailed JSON with timestamps
+ * - `vtt`: VTT subtitle format
+ * - `diarized_json`: JSON with speaker annotations (gpt-4o-transcribe-diarize only)
  *
- * Note: `diarized_json` is only available with `gpt-4o-transcribe-diarize` model.
- * GPT-4o transcribe models only support `json` format.
+ * Note: GPT-4o transcribe models only support `json` format.
+ * For diarization, use `diarized_json` with `gpt-4o-transcribe-diarize` model.
  *
  * @example
  * ```typescript
  * import { OpenAIResponseFormat } from 'voice-router-dev/constants'
  *
  * { responseFormat: OpenAIResponseFormat.verbose_json }
- * { responseFormat: OpenAIResponseFormat.srt }
+ * { responseFormat: OpenAIResponseFormat.diarized_json }
  * ```
  */
 declare const OpenAIResponseFormat: {
@@ -935,4 +984,4 @@ type OpenAIModelType = (typeof OpenAIModel)[keyof typeof OpenAIModel];
 /** OpenAI response format type derived from const object */
 type OpenAIResponseFormatType = (typeof OpenAIResponseFormat)[keyof typeof OpenAIResponseFormat];
 
-export { AssemblyAIEncoding, type AssemblyAIEncodingType, AssemblyAISampleRate, type AssemblyAISampleRateType, AssemblyAISpeechModel, type AssemblyAISpeechModelType, AssemblyAIStatus, type AssemblyAIStatusType, AzureStatus, type AzureStatusType, DeepgramCallbackMethod, type DeepgramCallbackMethodType, DeepgramEncoding, type DeepgramEncodingType, DeepgramIntentMode, type DeepgramIntentModeType, DeepgramModel, type DeepgramModelType, DeepgramRedact, type DeepgramRedactType, DeepgramRegion, type DeepgramRegionType, DeepgramSampleRate, type DeepgramSampleRateType, DeepgramStatus, type DeepgramStatusType, DeepgramTTSContainer, type DeepgramTTSContainerType, DeepgramTTSEncoding, type DeepgramTTSEncodingType, DeepgramTTSModel, type DeepgramTTSModelType, DeepgramTTSSampleRate, type DeepgramTTSSampleRateType, DeepgramTopicMode, type DeepgramTopicModeType, GladiaBitDepth, type GladiaBitDepthType, GladiaEncoding, type GladiaEncodingType, GladiaLanguage, type GladiaLanguageType, GladiaModel, type GladiaModelType, GladiaRegion, type GladiaRegionType, GladiaSampleRate, type GladiaSampleRateType, GladiaStatus, type GladiaStatusType, GladiaTranslationLanguage, type GladiaTranslationLanguageType, OpenAIModel, type OpenAIModelType, OpenAIResponseFormat, type OpenAIResponseFormatType, SpeechmaticsRegion, type SpeechmaticsRegionType };
+export { AssemblyAIEncoding, type AssemblyAIEncodingType, AssemblyAISampleRate, type AssemblyAISampleRateType, AssemblyAISpeechModel, type AssemblyAISpeechModelType, AssemblyAIStatus, type AssemblyAIStatusType, AzureStatus, type AzureStatusType, DeepgramCallbackMethod, type DeepgramCallbackMethodType, DeepgramEncoding, type DeepgramEncodingType, DeepgramIntentMode, type DeepgramIntentModeType, DeepgramModel, type DeepgramModelType, DeepgramRedact, type DeepgramRedactType, DeepgramRegion, type DeepgramRegionType, DeepgramSampleRate, type DeepgramSampleRateType, DeepgramStatus, type DeepgramStatusType, DeepgramTTSContainer, type DeepgramTTSContainerType, DeepgramTTSEncoding, type DeepgramTTSEncodingType, DeepgramTTSModel, type DeepgramTTSModelType, DeepgramTTSSampleRate, type DeepgramTTSSampleRateType, DeepgramTopicMode, type DeepgramTopicModeType, GladiaBitDepth, type GladiaBitDepthType, GladiaEncoding, type GladiaEncodingType, GladiaLanguage, type GladiaLanguageType, GladiaModel, type GladiaModelType, GladiaRegion, type GladiaRegionType, GladiaSampleRate, type GladiaSampleRateType, GladiaStatus, type GladiaStatusType, GladiaTranslationLanguage, type GladiaTranslationLanguageType, OpenAIModel, type OpenAIModelType, OpenAIResponseFormat, type OpenAIResponseFormatType, SonioxRegion, type SonioxRegionType, SpeechmaticsRegion, type SpeechmaticsRegionType };

package/dist/constants.js

@@ -49,6 +49,7 @@ __export(constants_exports, {
   GladiaTranslationLanguage: () => GladiaTranslationLanguage,
   OpenAIModel: () => OpenAIModel,
   OpenAIResponseFormat: () => OpenAIResponseFormat,
+  SonioxRegion: () => SonioxRegion,
   SpeechmaticsRegion: () => SpeechmaticsRegion
 });
 module.exports = __toCommonJS(constants_exports);
@@ -70,38 +71,22 @@ var ListenV1RedactParameterOneOfItem = {
   numbers: "numbers"
 };
 
-// src/generated/deepgram/schema/sharedCustomTopicModeParameter.ts
-var SharedCustomTopicModeParameter = {
-  extended: "extended",
-  strict: "strict"
-};
-
-// src/generated/deepgram/schema/sharedCustomIntentModeParameter.ts
-var SharedCustomIntentModeParameter = {
-  extended: "extended",
-  strict: "strict"
-};
-
 // src/generated/deepgram/schema/sharedCallbackMethodParameter.ts
 var SharedCallbackMethodParameter = {
   POST: "POST",
   PUT: "PUT"
 };
 
-// src/generated/gladia/schema/streamingSupportedEncodingEnum.ts
-var StreamingSupportedEncodingEnum = {
-  "wav/pcm": "wav/pcm",
-  "wav/alaw": "wav/alaw",
-  "wav/ulaw": "wav/ulaw"
+// src/generated/deepgram/schema/sharedCustomIntentModeParameter.ts
+var SharedCustomIntentModeParameter = {
+  extended: "extended",
+  strict: "strict"
 };
 
-// src/generated/gladia/schema/streamingSupportedSampleRateEnum.ts
-var StreamingSupportedSampleRateEnum = {
-  NUMBER_8000: 8e3,
-  NUMBER_16000: 16e3,
-  NUMBER_32000: 32e3,
-  NUMBER_44100: 44100,
-  NUMBER_48000: 48e3
+// src/generated/deepgram/schema/sharedCustomTopicModeParameter.ts
+var SharedCustomTopicModeParameter = {
+  extended: "extended",
+  strict: "strict"
 };
 
 // src/generated/gladia/schema/streamingSupportedBitDepthEnum.ts
@@ -112,6 +97,13 @@ var StreamingSupportedBitDepthEnum = {
   NUMBER_32: 32
 };
 
+// src/generated/gladia/schema/streamingSupportedEncodingEnum.ts
+var StreamingSupportedEncodingEnum = {
+  "wav/pcm": "wav/pcm",
+  "wav/alaw": "wav/alaw",
+  "wav/ulaw": "wav/ulaw"
+};
+
 // src/generated/gladia/schema/streamingSupportedModels.ts
 var StreamingSupportedModels = {
   "solaria-1": "solaria-1"
@@ -123,6 +115,15 @@ var StreamingSupportedRegions = {
   "eu-west": "eu-west"
 };
 
+// src/generated/gladia/schema/streamingSupportedSampleRateEnum.ts
+var StreamingSupportedSampleRateEnum = {
+  NUMBER_8000: 8e3,
+  NUMBER_16000: 16e3,
+  NUMBER_32000: 32e3,
+  NUMBER_44100: 44100,
+  NUMBER_48000: 48e3
+};
+
 // src/generated/gladia/schema/transcriptionLanguageCodeEnum.ts
 var TranscriptionLanguageCodeEnum = {
   af: "af",
@@ -338,14 +339,6 @@ var TranscriptStatus = {
   error: "error"
 };
 
-// src/generated/gladia/schema/transcriptionControllerListV2StatusItem.ts
-var TranscriptionControllerListV2StatusItem = {
-  queued: "queued",
-  processing: "processing",
-  done: "done",
-  error: "error"
-};
-
 // src/generated/azure/schema/status.ts
 var Status = {
   NotStarted: "NotStarted",
@@ -360,6 +353,32 @@ var ManageV1FilterStatusParameter = {
   failed: "failed"
 };
 
+// src/generated/gladia/schema/transcriptionControllerListV2StatusItem.ts
+var TranscriptionControllerListV2StatusItem = {
+  queued: "queued",
+  processing: "processing",
+  done: "done",
+  error: "error"
+};
+
+// src/generated/deepgram/schema/speakV1ContainerParameter.ts
+var SpeakV1ContainerParameter = {
+  none: "none",
+  wav: "wav",
+  ogg: "ogg"
+};
+
+// src/generated/deepgram/schema/speakV1EncodingParameter.ts
+var SpeakV1EncodingParameter = {
+  linear16: "linear16",
+  aac: "aac",
+  opus: "opus",
+  mp3: "mp3",
+  flac: "flac",
+  mulaw: "mulaw",
+  alaw: "alaw"
+};
+
 // src/generated/deepgram/schema/speakV1ModelParameter.ts
 var SpeakV1ModelParameter = {
   "aura-asteria-en": "aura-asteria-en",
@@ -427,24 +446,6 @@ var SpeakV1ModelParameter = {
   "aura-2-javier-es": "aura-2-javier-es"
 };
 
-// src/generated/deepgram/schema/speakV1EncodingParameter.ts
-var SpeakV1EncodingParameter = {
-  linear16: "linear16",
-  aac: "aac",
-  opus: "opus",
-  mp3: "mp3",
-  flac: "flac",
-  mulaw: "mulaw",
-  alaw: "alaw"
-};
-
-// src/generated/deepgram/schema/speakV1ContainerParameter.ts
-var SpeakV1ContainerParameter = {
-  none: "none",
-  wav: "wav",
-  ogg: "ogg"
-};
-
 // src/generated/deepgram/schema/speakV1SampleRateParameter.ts
 var SpeakV1SampleRateParameter = {
   NUMBER_8000: 8e3,
@@ -456,14 +457,6 @@ var SpeakV1SampleRateParameter = {
   null: null
 };
 
-// src/generated/openai/schema/audioTranscriptionModel.ts
-var AudioTranscriptionModel = {
-  "whisper-1": "whisper-1",
-  "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe",
-  "gpt-4o-transcribe": "gpt-4o-transcribe",
-  "gpt-4o-transcribe-diarize": "gpt-4o-transcribe-diarize"
-};
-
 // src/generated/openai/schema/audioResponseFormat.ts
 var AudioResponseFormat = {
   json: "json",
@@ -571,11 +564,25 @@ var DeepgramRegion = {
   /** European Union endpoint */
   eu: "eu"
 };
+var SonioxRegion = {
+  /** United States (default) */
+  us: "us",
+  /** European Union */
+  eu: "eu",
+  /** Japan */
+  jp: "jp"
+};
 var DeepgramTTSModel = SpeakV1ModelParameter;
 var DeepgramTTSEncoding = SpeakV1EncodingParameter;
 var DeepgramTTSContainer = SpeakV1ContainerParameter;
 var DeepgramTTSSampleRate = SpeakV1SampleRateParameter;
-var OpenAIModel = AudioTranscriptionModel;
+var OpenAIModel = {
+  "whisper-1": "whisper-1",
+  "gpt-4o-transcribe": "gpt-4o-transcribe",
+  "gpt-4o-mini-transcribe": "gpt-4o-mini-transcribe",
+  "gpt-4o-mini-transcribe-2025-12-15": "gpt-4o-mini-transcribe-2025-12-15",
+  "gpt-4o-transcribe-diarize": "gpt-4o-transcribe-diarize"
+};
 var OpenAIResponseFormat = AudioResponseFormat;
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
@@ -607,6 +614,7 @@ var OpenAIResponseFormat = AudioResponseFormat;
   GladiaTranslationLanguage,
   OpenAIModel,
   OpenAIResponseFormat,
+  SonioxRegion,
   SpeechmaticsRegion
 });
 //# sourceMappingURL=constants.js.map