Merge pull request #524 from deepgram/lo/tts-ws-release

feat: officially enable aura-2 in live text-to-speech

Author: naomi-lgbt

deepgram/clients/speak/v1/rest/options.py

@@ -23,7 +23,7 @@ class SpeakRESTOptions(BaseResponse):
     """
 
     model: Optional[str] = field(
-        default="aura-asteria-en",
+        default="aura-2-thalia-en",
         metadata=dataclass_config(exclude=lambda f: f is None),
     )
     encoding: Optional[str] = field(

deepgram/clients/speak/v1/websocket/options.py

@@ -23,7 +23,7 @@ class SpeakWSOptions(BaseResponse):
     """
 
     model: Optional[str] = field(
-        default="aura-asteria-en",
+        default="aura-2-thalia-en",
         metadata=dataclass_config(exclude=lambda f: f is None),
     )
     encoding: Optional[str] = field(

examples/text-to-speech/websocket/async_simple/main.py

@@ -90,7 +90,7 @@ async def on_unhandled(self, unhandled, **kwargs):
 
         # connect to websocket
         options = SpeakWSOptions(
-            model="aura-asteria-en",
+            model="aura-2-thalia-en",
             encoding="linear16",
             sample_rate=16000,
         )

examples/text-to-speech/websocket/output_to_wav/main.py

@@ -57,7 +57,7 @@ def on_close(self, close, **kwargs):
 
         # connect to websocket
         options = SpeakWSOptions(
-            model="aura-asteria-en",
+            model="aura-2-thalia-en",
             encoding="linear16",
             sample_rate=16000,
         )

examples/text-to-speech/websocket/simple/main.py

@@ -81,7 +81,7 @@ def on_unhandled(self, unhandled, **kwargs):
 
         # connect to websocket
         options = SpeakWSOptions(
-            model="aura-asteria-en",
+            model="aura-2-thalia-en",
             encoding="linear16",
             sample_rate=16000,
         )

tests/daily_test/test_daily_async_speak_rest.py

@@ -12,7 +12,7 @@
 
 from tests.utils import save_metadata_string
 
-TTS_MODEL = "aura-asteria-en"
+TTS_MODEL = "aura-2-thalia-en"
 STT_MODEL = "general-nova-3"
 
 # response constants

tests/daily_test/test_daily_speak_rest.py

@@ -12,7 +12,7 @@
 
 from tests.utils import save_metadata_string
 
-TTS_MODEL = "aura-asteria-en"
+TTS_MODEL = "aura-2-thalia-en"
 STT_MODEL = "general-nova-3"
 
 # response constants

tests/response_data/listen/rest/a231370d439312b1a404bb6ad8de955e900ec8eae9a906329af8cc672e6ec7ba-29e7c8100617f70da4ae9da1921cb5071a01219f4780ca70930b0a370ed2163a-response.json

@@ -1 +1 @@
-{"metadata": {"transaction_key": "deprecated", "request_id": "2416b924-5d87-433b-947b-ee694dcee412", "sha256": "5324da68ede209a16ac69a38e8cd29cee4d754434a041166cda3a1f5e0b24566", "created": "2025-02-07T01:53:25.648Z", "duration": 17.566313, "channels": 1, "models": ["3b3aabe4-608a-46ac-9585-7960a25daf1a"], "model_info": {"3b3aabe4-608a-46ac-9585-7960a25daf1a": {"name": "general-nova-3", "version": "2024-12-20.0", "arch": "nova-3"}}, "summary_info": {"model_uuid": "67875a7f-c9c4-48a0-aa55-5bdb8a91c34a", "input_tokens": 0, "output_tokens": 0}}, "results": {"channels": [{"alternatives": [{"transcript": "Yep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it.", "confidence": 0.99902344, "words": [{"word": "yep", "start": 5.52, "end": 6.2400002, "confidence": 0.9238281, "punctuated_word": "Yep."}, {"word": "i", "start": 6.96, "end": 7.2799997, "confidence": 0.5800781, "punctuated_word": "I"}, {"word": "said", "start": 7.2799997, "end": 7.52, "confidence": 0.90527344, "punctuated_word": "said"}, {"word": "it", "start": 7.52, "end": 7.68, "confidence": 0.9980469, "punctuated_word": "it"}, {"word": "before", "start": 7.68, "end": 8.08, "confidence": 0.89331055, "punctuated_word": "before,"}, {"word": "and", "start": 8.08, "end": 8.16, "confidence": 1.0, "punctuated_word": "and"}, {"word": "i'll", "start": 8.16, "end": 8.4, "confidence": 1.0, "punctuated_word": "I'll"}, {"word": "say", "start": 8.4, "end": 8.48, "confidence": 1.0, "punctuated_word": "say"}, {"word": "it", "start": 8.48, "end": 8.639999, "confidence": 1.0, "punctuated_word": "it"}, {"word": "again", "start": 8.639999, "end": 9.28, "confidence": 0.953125, "punctuated_word": "again."}, {"word": "life", "start": 10.071313, "end": 10.311313, "confidence": 0.99902344, "punctuated_word": "Life"}, {"word": "moves", "start": 10.311313, "end": 10.631312, "confidence": 1.0, "punctuated_word": "moves"}, {"word": "pretty", "start": 10.631312, "end": 11.031313, "confidence": 1.0, "punctuated_word": "pretty"}, {"word": "fast", "start": 11.031313, "end": 11.671312, "confidence": 0.99902344, "punctuated_word": "fast."}, {"word": "you", "start": 12.071312, "end": 12.311313, "confidence": 0.92089844, "punctuated_word": "You"}, {"word": "don't", "start": 12.311313, "end": 12.551312, "confidence": 1.0, "punctuated_word": "don't"}, {"word": "stop", "start": 12.551312, "end": 12.791312, "confidence": 1.0, "punctuated_word": "stop"}, {"word": "and", "start": 12.791312, "end": 12.951312, "confidence": 0.99902344, "punctuated_word": "and"}, {"word": "look", "start": 12.951312, "end": 13.111313, "confidence": 1.0, "punctuated_word": "look"}, {"word": "around", "start": 13.111313, "end": 13.351313, "confidence": 1.0, "punctuated_word": "around"}, {"word": "once", "start": 13.351313, "end": 13.671312, "confidence": 0.99902344, "punctuated_word": "once"}, {"word": "in", "start": 13.671312, "end": 13.831312, "confidence": 0.9970703, "punctuated_word": "in"}, {"word": "a", "start": 13.831312, "end": 13.911312, "confidence": 0.98535156, "punctuated_word": "a"}, {"word": "while", "start": 13.911312, "end": 14.391312, "confidence": 0.93530273, "punctuated_word": "while,"}, {"word": "you", "start": 14.711312, "end": 14.871312, "confidence": 0.99902344, "punctuated_word": "you"}, {"word": "could", "start": 14.871312, "end": 15.031313, "confidence": 1.0, "punctuated_word": "could"}, {"word": "miss", "start": 15.031313, "end": 15.271313, "confidence": 1.0, "punctuated_word": "miss"}, {"word": "it", "start": 15.271313, "end": 15.831312, "confidence": 0.99902344, "punctuated_word": "it."}], "paragraphs": {"transcript": "\nYep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it.", "paragraphs": [{"sentences": [{"text": "Yep.", "start": 5.52, "end": 6.2400002}, {"text": "I said it before, and I'll say it again.", "start": 6.96, "end": 9.28}, {"text": "Life moves pretty fast.", "start": 10.071313, "end": 11.671312}, {"text": "You don't stop and look around once in a while, you could miss it.", "start": 12.071312, "end": 15.831312}], "start": 5.52, "end": 15.831312, "num_words": 28}]}}]}], "summary": {"result": "success", "short": "Yep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it."}}}
+{"metadata": {"transaction_key": "deprecated", "request_id": "f3993870-9318-415d-9303-ad0fa2af43d2", "sha256": "5324da68ede209a16ac69a38e8cd29cee4d754434a041166cda3a1f5e0b24566", "created": "2025-05-09T20:14:12.218Z", "duration": 17.566313, "channels": 1, "models": ["3b3aabe4-608a-46ac-9585-7960a25daf1a"], "model_info": {"3b3aabe4-608a-46ac-9585-7960a25daf1a": {"name": "general-nova-3", "version": "2024-12-20.0", "arch": "nova-3"}}, "summary_info": {"model_uuid": "67875a7f-c9c4-48a0-aa55-5bdb8a91c34a", "input_tokens": 0, "output_tokens": 0}}, "results": {"channels": [{"alternatives": [{"transcript": "Yep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it.", "confidence": 0.999143, "words": [{"word": "yep", "start": 5.52, "end": 6.2400002, "confidence": 0.92342806, "punctuated_word": "Yep."}, {"word": "i", "start": 6.96, "end": 7.2799997, "confidence": 0.57757515, "punctuated_word": "I"}, {"word": "said", "start": 7.2799997, "end": 7.52, "confidence": 0.9052356, "punctuated_word": "said"}, {"word": "it", "start": 7.52, "end": 7.68, "confidence": 0.99797314, "punctuated_word": "it"}, {"word": "before", "start": 7.68, "end": 8.08, "confidence": 0.8933872, "punctuated_word": "before,"}, {"word": "and", "start": 8.08, "end": 8.16, "confidence": 0.99981827, "punctuated_word": "and"}, {"word": "i'll", "start": 8.16, "end": 8.4, "confidence": 0.99961716, "punctuated_word": "I'll"}, {"word": "say", "start": 8.4, "end": 8.48, "confidence": 0.99941766, "punctuated_word": "say"}, {"word": "it", "start": 8.48, "end": 8.639999, "confidence": 0.999597, "punctuated_word": "it"}, {"word": "again", "start": 8.639999, "end": 8.96, "confidence": 0.9528253, "punctuated_word": "again."}, {"word": "life", "start": 10.071313, "end": 10.311313, "confidence": 0.9990013, "punctuated_word": "Life"}, {"word": "moves", "start": 10.311313, "end": 10.631312, "confidence": 0.9996643, "punctuated_word": "moves"}, {"word": "pretty", "start": 10.631312, "end": 11.031313, "confidence": 0.99988604, "punctuated_word": "pretty"}, {"word": "fast", "start": 11.031313, "end": 11.671312, "confidence": 0.9989686, "punctuated_word": "fast."}, {"word": "you", "start": 12.071312, "end": 12.311313, "confidence": 0.92013294, "punctuated_word": "You"}, {"word": "don't", "start": 12.311313, "end": 12.551312, "confidence": 0.99986017, "punctuated_word": "don't"}, {"word": "stop", "start": 12.551312, "end": 12.791312, "confidence": 0.99976414, "punctuated_word": "stop"}, {"word": "and", "start": 12.791312, "end": 12.951312, "confidence": 0.99852246, "punctuated_word": "and"}, {"word": "look", "start": 12.951312, "end": 13.111313, "confidence": 0.9998677, "punctuated_word": "look"}, {"word": "around", "start": 13.111313, "end": 13.351313, "confidence": 0.9998548, "punctuated_word": "around"}, {"word": "once", "start": 13.351313, "end": 13.671312, "confidence": 0.999143, "punctuated_word": "once"}, {"word": "in", "start": 13.671312, "end": 13.831312, "confidence": 0.9976291, "punctuated_word": "in"}, {"word": "a", "start": 13.831312, "end": 13.911312, "confidence": 0.98508644, "punctuated_word": "a"}, {"word": "while", "start": 13.911312, "end": 14.391312, "confidence": 0.9349461, "punctuated_word": "while,"}, {"word": "you", "start": 14.711312, "end": 14.871312, "confidence": 0.99921596, "punctuated_word": "you"}, {"word": "could", "start": 14.871312, "end": 15.031313, "confidence": 0.99974436, "punctuated_word": "could"}, {"word": "miss", "start": 15.031313, "end": 15.271313, "confidence": 0.9997112, "punctuated_word": "miss"}, {"word": "it", "start": 15.271313, "end": 15.5113125, "confidence": 0.99891484, "punctuated_word": "it."}], "paragraphs": {"transcript": "\nYep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it.", "paragraphs": [{"sentences": [{"text": "Yep.", "start": 5.52, "end": 6.2400002}, {"text": "I said it before, and I'll say it again.", "start": 6.96, "end": 8.96}, {"text": "Life moves pretty fast.", "start": 10.071313, "end": 11.671312}, {"text": "You don't stop and look around once in a while, you could miss it.", "start": 12.071312, "end": 15.5113125}], "start": 5.52, "end": 15.5113125, "num_words": 28}]}}]}], "summary": {"result": "success", "short": "Yep. I said it before, and I'll say it again. Life moves pretty fast. You don't stop and look around once in a while, you could miss it."}}}

tests/response_data/listen/rest/a231370d439312b1a404bb6ad8de955e900ec8eae9a906329af8cc672e6ec7ba-a17f4880c5b4cf124ac54d06d77c9f0ab7f3fe1052ff1c7b090f7eaf8ede5b76-error.json

@@ -1 +1 @@
-{"actual": "Speaker 1 discusses the goal of establishing a more perfect union, justice, and the common defense for the United States of America, in order to secure the blessings of liberty and establish the constitution for the country.", "expected": ["*"]}
+{"actual": "Speaker 1 discusses the goal of establishing a more perfect union, justice, and the common defense for the United States of America, as part of the Better Union movement.", "expected": ["*"]}