@volley/recognition-client-sdk 0.1.621 → 0.1.670

package/dist/browser.bundled.d.ts

@@ -12,11 +12,14 @@ declare enum RecognitionProvider {
     DEEPGRAM = "deepgram",
     ELEVENLABS = "elevenlabs",
     FIREWORKS = "fireworks",
+    GLADIA = "gladia",
     GOOGLE = "google",
     GEMINI_BATCH = "gemini-batch",
     OPENAI_BATCH = "openai-batch",
+    SELF_SERVE_VLLM = "self-serve-vllm",
     OPENAI_REALTIME = "openai-realtime",
     MISTRAL_VOXTRAL = "mistral-voxtral",
+    CARTESIA = "cartesia",
     DASHSCOPE = "dashscope",
     TEST_ASR_PROVIDER_QUOTA = "test-asr-provider-quota",
     TEST_ASR_STREAMING = "test-asr-streaming"
@@ -67,6 +70,13 @@ declare enum FireworksModel {
     WHISPER_V3 = "whisper-v3",
     WHISPER_V3_TURBO = "whisper-v3-turbo"
 }
+/**
+ * Gladia Solaria realtime transcription models
+ * @see https://docs.gladia.io/api-reference/v2/live/init
+ */
+declare enum GladiaModel {
+    SOLARIA_1 = "solaria-1"
+}
 /**
  * ElevenLabs Scribe models for speech-to-text
  * @see https://elevenlabs.io/blog/introducing-scribe-v2-realtime
@@ -74,8 +84,7 @@ declare enum FireworksModel {
  * @see https://elevenlabs.io/docs/api-reference/speech-to-text/convert
  */
 declare enum ElevenLabsModel {
-    SCRIBE_V2_REALTIME = "scribe_v2_realtime",
-    SCRIBE_V1 = "scribe_v1"
+    SCRIBE_V2_REALTIME = "scribe_v2_realtime"
 }
 /**
  * OpenAI Realtime API transcription models
@@ -94,6 +103,14 @@ declare enum OpenAIRealtimeModel {
 declare enum MistralVoxtralModel {
     VOXTRAL_MINI_REALTIME_2602 = "voxtral-mini-transcribe-realtime-2602"
 }
+/**
+ * Cartesia Ink-Whisper Realtime transcription models
+ * @see https://docs.cartesia.ai/build-with-cartesia/stt-models
+ */
+declare enum CartesiaModel {
+    INK_WHISPER = "ink-whisper",
+    INK_WHISPER_20250604 = "ink-whisper-2025-06-04"
+}
 /**
  * DashScope Qwen-ASR Realtime transcription models
  * @see https://www.alibabacloud.com/help/en/model-studio/qwen-real-time-speech-recognition
@@ -102,10 +119,17 @@ declare enum DashScopeModel {
     QWEN3_ASR_FLASH_REALTIME_2602 = "qwen3-asr-flash-realtime-2026-02-10",
     QWEN3_ASR_FLASH_REALTIME = "qwen3-asr-flash-realtime"
 }
+/**
+ * Self-serve vLLM batch transcription models
+ * Backed by recognition-inference / RunPod `/transcribe`
+ */
+declare enum SelfServeVllmModel {
+    QWEN3_ASR_1_7B = "qwen3-asr-1.7b"
+}
 /**
  * Type alias for any model from any provider
  */
-type RecognitionModel = DeepgramModel | GoogleModel | FireworksModel | ElevenLabsModel | OpenAIRealtimeModel | MistralVoxtralModel | DashScopeModel | string;
+type RecognitionModel = DeepgramModel | GoogleModel | FireworksModel | GladiaModel | ElevenLabsModel | OpenAIRealtimeModel | MistralVoxtralModel | CartesiaModel | DashScopeModel | SelfServeVllmModel | string;
 
 /**
  * Audio encoding types
@@ -260,6 +284,7 @@ declare const TranscriptionResultSchemaV1: z.ZodObject<{
     voiceStart: z.ZodOptional<z.ZodNumber>;
     voiceDuration: z.ZodOptional<z.ZodNumber>;
     voiceEnd: z.ZodOptional<z.ZodNumber>;
+    lastNonSilence: z.ZodOptional<z.ZodNumber>;
     startTimestamp: z.ZodOptional<z.ZodNumber>;
     endTimestamp: z.ZodOptional<z.ZodNumber>;
     receivedAtMs: z.ZodOptional<z.ZodNumber>;
@@ -278,6 +303,7 @@ declare const TranscriptionResultSchemaV1: z.ZodObject<{
     voiceStart?: number | undefined;
     voiceDuration?: number | undefined;
     voiceEnd?: number | undefined;
+    lastNonSilence?: number | undefined;
     startTimestamp?: number | undefined;
     endTimestamp?: number | undefined;
     receivedAtMs?: number | undefined;
@@ -296,6 +322,7 @@ declare const TranscriptionResultSchemaV1: z.ZodObject<{
     voiceStart?: number | undefined;
     voiceDuration?: number | undefined;
     voiceEnd?: number | undefined;
+    lastNonSilence?: number | undefined;
     startTimestamp?: number | undefined;
     endTimestamp?: number | undefined;
     receivedAtMs?: number | undefined;
@@ -366,6 +393,8 @@ declare const MetadataResultSchemaV1: z.ZodObject<{
     rawAudioTimeMs: z.ZodOptional<z.ZodNumber>;
     costInUSD: z.ZodOptional<z.ZodDefault<z.ZodNumber>>;
     apiType: z.ZodOptional<z.ZodNativeEnum<typeof ASRApiType>>;
+    provider: z.ZodOptional<z.ZodString>;
+    model: z.ZodOptional<z.ZodString>;
     asrConfig: z.ZodOptional<z.ZodString>;
     rawAsrMetadata: z.ZodOptional<z.ZodString>;
     transcriptOutcome: z.ZodOptional<z.ZodNativeEnum<typeof TranscriptOutcomeType>>;
@@ -420,6 +449,8 @@ declare const MetadataResultSchemaV1: z.ZodObject<{
     rawAudioTimeMs?: number | undefined;
     costInUSD?: number | undefined;
     apiType?: ASRApiType | undefined;
+    provider?: string | undefined;
+    model?: string | undefined;
     asrConfig?: string | undefined;
     rawAsrMetadata?: string | undefined;
     transcriptOutcome?: TranscriptOutcomeType | undefined;
@@ -450,6 +481,8 @@ declare const MetadataResultSchemaV1: z.ZodObject<{
     rawAudioTimeMs?: number | undefined;
     costInUSD?: number | undefined;
     apiType?: ASRApiType | undefined;
+    provider?: string | undefined;
+    model?: string | undefined;
     asrConfig?: string | undefined;
     rawAsrMetadata?: string | undefined;
     transcriptOutcome?: TranscriptOutcomeType | undefined;