@volley/recognition-client-sdk 0.1.621 → 0.1.670

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -3737,11 +3737,14 @@ var RecognitionProvider;
3737
3737
  RecognitionProvider2["DEEPGRAM"] = "deepgram";
3738
3738
  RecognitionProvider2["ELEVENLABS"] = "elevenlabs";
3739
3739
  RecognitionProvider2["FIREWORKS"] = "fireworks";
3740
+ RecognitionProvider2["GLADIA"] = "gladia";
3740
3741
  RecognitionProvider2["GOOGLE"] = "google";
3741
3742
  RecognitionProvider2["GEMINI_BATCH"] = "gemini-batch";
3742
3743
  RecognitionProvider2["OPENAI_BATCH"] = "openai-batch";
3744
+ RecognitionProvider2["SELF_SERVE_VLLM"] = "self-serve-vllm";
3743
3745
  RecognitionProvider2["OPENAI_REALTIME"] = "openai-realtime";
3744
3746
  RecognitionProvider2["MISTRAL_VOXTRAL"] = "mistral-voxtral";
3747
+ RecognitionProvider2["CARTESIA"] = "cartesia";
3745
3748
  RecognitionProvider2["DASHSCOPE"] = "dashscope";
3746
3749
  RecognitionProvider2["TEST_ASR_PROVIDER_QUOTA"] = "test-asr-provider-quota";
3747
3750
  RecognitionProvider2["TEST_ASR_STREAMING"] = "test-asr-streaming";
@@ -3783,10 +3786,13 @@ var FireworksModel;
3783
3786
  FireworksModel2["WHISPER_V3"] = "whisper-v3";
3784
3787
  FireworksModel2["WHISPER_V3_TURBO"] = "whisper-v3-turbo";
3785
3788
  })(FireworksModel || (FireworksModel = {}));
3789
+ var GladiaModel;
3790
+ (function(GladiaModel2) {
3791
+ GladiaModel2["SOLARIA_1"] = "solaria-1";
3792
+ })(GladiaModel || (GladiaModel = {}));
3786
3793
  var ElevenLabsModel;
3787
3794
  (function(ElevenLabsModel2) {
3788
3795
  ElevenLabsModel2["SCRIBE_V2_REALTIME"] = "scribe_v2_realtime";
3789
- ElevenLabsModel2["SCRIBE_V1"] = "scribe_v1";
3790
3796
  })(ElevenLabsModel || (ElevenLabsModel = {}));
3791
3797
  var OpenAIRealtimeModel;
3792
3798
  (function(OpenAIRealtimeModel2) {
@@ -3797,11 +3803,20 @@ var MistralVoxtralModel;
3797
3803
  (function(MistralVoxtralModel2) {
3798
3804
  MistralVoxtralModel2["VOXTRAL_MINI_REALTIME_2602"] = "voxtral-mini-transcribe-realtime-2602";
3799
3805
  })(MistralVoxtralModel || (MistralVoxtralModel = {}));
3806
+ var CartesiaModel;
3807
+ (function(CartesiaModel2) {
3808
+ CartesiaModel2["INK_WHISPER"] = "ink-whisper";
3809
+ CartesiaModel2["INK_WHISPER_20250604"] = "ink-whisper-2025-06-04";
3810
+ })(CartesiaModel || (CartesiaModel = {}));
3800
3811
  var DashScopeModel;
3801
3812
  (function(DashScopeModel2) {
3802
3813
  DashScopeModel2["QWEN3_ASR_FLASH_REALTIME_2602"] = "qwen3-asr-flash-realtime-2026-02-10";
3803
3814
  DashScopeModel2["QWEN3_ASR_FLASH_REALTIME"] = "qwen3-asr-flash-realtime";
3804
3815
  })(DashScopeModel || (DashScopeModel = {}));
3816
+ var SelfServeVllmModel;
3817
+ (function(SelfServeVllmModel2) {
3818
+ SelfServeVllmModel2["QWEN3_ASR_1_7B"] = "qwen3-asr-1.7b";
3819
+ })(SelfServeVllmModel || (SelfServeVllmModel = {}));
3805
3820
 
3806
3821
  // ../../libs/types/dist/recognition-result-v1.types.js
3807
3822
  var RecognitionResultTypeV1;
@@ -3826,6 +3841,7 @@ var TranscriptionResultSchemaV1 = z.object({
3826
3841
  voiceStart: z.number().optional(),
3827
3842
  voiceDuration: z.number().optional(),
3828
3843
  voiceEnd: z.number().optional(),
3844
+ lastNonSilence: z.number().optional(),
3829
3845
  startTimestamp: z.number().optional(),
3830
3846
  endTimestamp: z.number().optional(),
3831
3847
  receivedAtMs: z.number().optional(),
@@ -3873,6 +3889,9 @@ var MetadataResultSchemaV1 = z.object({
3873
3889
  costInUSD: z.number().default(0).optional(),
3874
3890
  // ASR API Type
3875
3891
  apiType: z.nativeEnum(ASRApiType).optional(),
3892
+ // Provider identification
3893
+ provider: z.string().optional(),
3894
+ model: z.string().optional(),
3876
3895
  // ASR configuration as JSON string (no type validation)
3877
3896
  asrConfig: z.string().optional(),
3878
3897
  // Raw ASR metadata payload as provided by the provider (stringified if needed)
@@ -5180,7 +5199,7 @@ var MessageHandler = class {
5180
5199
  }
5181
5200
  if (msg.data && typeof msg.data !== "object") {
5182
5201
  if (this.callbacks.logger) {
5183
- this.callbacks.logger("error", "[RecogSDK] Received primitive msg.data from server", {
5202
+ this.callbacks.logger("warn", "[RecogSDK] Received primitive msg.data from server", {
5184
5203
  dataType: typeof msg.data,
5185
5204
  data: msg.data,
5186
5205
  fullMessage: msg
@@ -5435,7 +5454,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5435
5454
  const timeout = setTimeout(() => {
5436
5455
  if (settled) return;
5437
5456
  settled = true;
5438
- this.log("warn", "Connection timeout", { timeout: connectionTimeout, attempt });
5457
+ this.log("warn", `Connection timeout url=${this.config.url}`, { timeout: connectionTimeout, attempt });
5439
5458
  this.state = "failed" /* FAILED */;
5440
5459
  reject(new Error(`Connection timeout after ${connectionTimeout}ms`));
5441
5460
  }, connectionTimeout);
@@ -5457,7 +5476,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5457
5476
  if (settled) return;
5458
5477
  settled = true;
5459
5478
  clearTimeout(timeout);
5460
- this.log("warn", "Connection error", { error, attempt });
5479
+ this.log("warn", `Connection error url=${this.config.url}`, { error, attempt });
5461
5480
  this.state = "failed" /* FAILED */;
5462
5481
  reject(error);
5463
5482
  };
@@ -5472,14 +5491,14 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5472
5491
  lastError = error;
5473
5492
  if (attempt < maxAttempts) {
5474
5493
  const logLevel = attempt < 3 ? "info" : "warn";
5475
- this.log(logLevel, `Connection attempt ${attempt} failed, retrying after ${delayMs}ms`, {
5494
+ this.log(logLevel, `Connection attempt ${attempt} failed, retrying after ${delayMs}ms url=${this.config.url}`, {
5476
5495
  error: lastError.message,
5477
5496
  nextAttempt: attempt + 1
5478
5497
  });
5479
5498
  this.state = "initial" /* INITIAL */;
5480
5499
  await new Promise((resolve) => setTimeout(resolve, delayMs));
5481
5500
  } else {
5482
- this.log("warn", `All ${maxAttempts} connection attempts failed`, {
5501
+ this.log("warn", `All ${maxAttempts} connection attempts failed url=${this.config.url}`, {
5483
5502
  error: lastError.message
5484
5503
  });
5485
5504
  }
@@ -5502,7 +5521,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5502
5521
  blobToArrayBuffer(audioData).then((arrayBuffer) => {
5503
5522
  this.sendAudioInternal(arrayBuffer);
5504
5523
  }).catch((error) => {
5505
- this.log("error", "Failed to convert Blob to ArrayBuffer", error);
5524
+ this.log("warn", "Failed to convert Blob to ArrayBuffer", error);
5506
5525
  });
5507
5526
  return;
5508
5527
  }
@@ -5542,7 +5561,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5542
5561
  */
5543
5562
  async stopRecording() {
5544
5563
  if (this.state !== "ready" /* READY */) {
5545
- this.log("warn", "stopRecording called but not in READY state", { state: this.state });
5564
+ this.log("info", "stopRecording called but not in READY state", { state: this.state });
5546
5565
  return;
5547
5566
  }
5548
5567
  this.log("debug", "Stopping recording");
@@ -5712,7 +5731,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5712
5731
  if (this.state === "stopping" /* STOPPING */) {
5713
5732
  this.state = "stopped" /* STOPPED */;
5714
5733
  } else if (this.state === "connected" /* CONNECTED */ || this.state === "ready" /* READY */ || this.state === "connecting" /* CONNECTING */) {
5715
- this.log("error", "[DIAGNOSTIC] Unexpected disconnection", {
5734
+ this.log("warn", "[DIAGNOSTIC] Unexpected disconnection", {
5716
5735
  code,
5717
5736
  codeDescription: closeCodeDescription,
5718
5737
  reason: reason || "(empty)",
@@ -5834,7 +5853,7 @@ var RealTimeTwoWayWebSocketRecognitionClient = class _RealTimeTwoWayWebSocketRec
5834
5853
  blobToArrayBuffer(audioData).then((arrayBuffer) => {
5835
5854
  this.sendPrefixAudioInternal(arrayBuffer);
5836
5855
  }).catch((error) => {
5837
- this.log("error", "Failed to convert Blob to ArrayBuffer for prefix audio", error);
5856
+ this.log("warn", "Failed to convert Blob to ArrayBuffer for prefix audio", error);
5838
5857
  });
5839
5858
  return;
5840
5859
  }