Merge pull request #1497 from pipecat-ai/mb/gladia-languages

Align languages with Gladia's supported languages, remove audio_enhancer option

CHANGELOG.md

@@ -70,7 +70,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `pipecat.services.[ai_service,image_service,llm_service,stt_service,vision_service]`.
 
 - `GladiaSTTService` now uses the `solaria-1` model by default. Other params
-  use Gladia's default values.
+  use Gladia's default values. Added support for more language codes.
 
 ### Fixed
 

src/pipecat/services/gladia/config.py

@@ -27,11 +27,9 @@ class PreProcessingConfig(BaseModel):
     """Configuration for audio pre-processing options.
 
     Attributes:
-        audio_enhancer: Whether to apply audio enhancement
         speech_threshold: Sensitivity for speech detection (0-1)
     """
 
-    audio_enhancer: Optional[bool] = None
     speech_threshold: Optional[float] = None
 
 

src/pipecat/services/gladia/stt.py

@@ -48,8 +48,12 @@ def language_to_gladia_language(language: Language) -> Optional[str]:
         Language.AR: "ar",
         Language.AS: "as",
         Language.AZ: "az",
+        Language.BA: "ba",
+        Language.BE: "be",
         Language.BG: "bg",
         Language.BN: "bn",
+        Language.BO: "bo",
+        Language.BR: "br",
         Language.BS: "bs",
         Language.CA: "ca",
         Language.CS: "cs",
@@ -63,13 +67,16 @@ def language_to_gladia_language(language: Language) -> Optional[str]:
         Language.EU: "eu",
         Language.FA: "fa",
         Language.FI: "fi",
+        Language.FO: "fo",
         Language.FR: "fr",
-        Language.GA: "ga",
         Language.GL: "gl",
         Language.GU: "gu",
+        Language.HA: "ha",
+        Language.HAW: "haw",
         Language.HE: "he",
         Language.HI: "hi",
         Language.HR: "hr",
+        Language.HT: "ht",
         Language.HU: "hu",
         Language.HY: "hy",
         Language.ID: "id",
@@ -82,29 +89,38 @@ def language_to_gladia_language(language: Language) -> Optional[str]:
         Language.KM: "km",
         Language.KN: "kn",
         Language.KO: "ko",
+        Language.LA: "la",
+        Language.LB: "lb",
+        Language.LN: "ln",
         Language.LO: "lo",
         Language.LT: "lt",
         Language.LV: "lv",
+        Language.MG: "mg",
+        Language.MI: "mi",
         Language.MK: "mk",
         Language.ML: "ml",
         Language.MN: "mn",
         Language.MR: "mr",
         Language.MS: "ms",
         Language.MT: "mt",
-        Language.MY: "my",
+        Language.MY_MR: "mymr",
         Language.NE: "ne",
         Language.NL: "nl",
+        Language.NN: "nn",
         Language.NO: "no",
-        Language.OR: "or",
+        Language.OC: "oc",
         Language.PA: "pa",
         Language.PL: "pl",
         Language.PS: "ps",
         Language.PT: "pt",
         Language.RO: "ro",
         Language.RU: "ru",
+        Language.SA: "sa",
+        Language.SD: "sd",
         Language.SI: "si",
         Language.SK: "sk",
         Language.SL: "sl",
+        Language.SN: "sn",
         Language.SO: "so",
         Language.SQ: "sq",
         Language.SR: "sr",
@@ -113,14 +129,19 @@ def language_to_gladia_language(language: Language) -> Optional[str]:
         Language.SW: "sw",
         Language.TA: "ta",
         Language.TE: "te",
+        Language.TG: "tg",
         Language.TH: "th",
+        Language.TK: "tk",
+        Language.TL: "tl",
         Language.TR: "tr",
+        Language.TT: "tt",
         Language.UK: "uk",
         Language.UR: "ur",
         Language.UZ: "uz",
         Language.VI: "vi",
+        Language.YI: "yi",
+        Language.YO: "yo",
         Language.ZH: "zh",
-        Language.ZU: "zu",
     }
 
     result = BASE_LANGUAGES.get(language)

src/pipecat/transcriptions/language.py

@@ -182,6 +182,9 @@ class Language(StrEnum):
     GA = "ga"
     GA_IE = "ga-IE"
 
+    # Gaelic
+    GD = "gd"
+
     # Galician
     GL = "gl"
     GL_ES = "gl-ES"
@@ -193,6 +196,9 @@ class Language(StrEnum):
     # Hausa
     HA = "ha"
 
+    # Hawaiian
+    HAW = "haw"
+
     # Hebrew
     HE = "he"
     HE_IL = "he-IL"
@@ -288,6 +294,9 @@ class Language(StrEnum):
     # Malagasy
     MG = "mg"
 
+    # Maori
+    MI = "mi"
+
     # Macedonian
     MK = "mk"
     MK_MK = "mk-MK"
@@ -300,9 +309,6 @@ class Language(StrEnum):
     MN = "mn"
     MN_MN = "mn-MN"
 
-    # Maori
-    MI = "mi"
-
     # Marathi
     MR = "mr"
     MR_IN = "mr-IN"
@@ -318,6 +324,7 @@ class Language(StrEnum):
     # Burmese
     MY = "my"
     MY_MM = "my-MM"
+    MY_MR = "mymr"
 
     # Norwegian
     NB = "nb"  # Norwegian Bokmål
@@ -414,9 +421,6 @@ class Language(StrEnum):
     SW_KE = "sw-KE"
     SW_TZ = "sw-TZ"
 
-    # Tagalog
-    TL = "tl"
-
     # Tamil
     TA = "ta"
     TA_IN = "ta-IN"
@@ -438,6 +442,9 @@ class Language(StrEnum):
     # Turkmen
     TK = "tk"
 
+    # Tagalog
+    TL = "tl"
+
     # Turkish
     TR = "tr"
     TR_TR = "tr-TR"
@@ -489,7 +496,7 @@ class Language(StrEnum):
     ZH_TW = "zh-TW"
 
     # Xhosa
-    XH = "xh"
+    XH = "xh-ZA"
 
     # Zulu
     ZU = "zu"