transcriptions: added more languages

src/pipecat/services/cartesia.py

@@ -26,7 +26,7 @@ from pipecat.frames.frames import (
     LLMFullResponseEndFrame
 )
 from pipecat.processors.frame_processor import FrameDirection
-from pipecat.transcriptions.languages import Language
+from pipecat.transcriptions.language import Language
 from pipecat.services.ai_services import TTSService
 
 from loguru import logger
@@ -43,10 +43,20 @@ except ModuleNotFoundError as e:
 
 def language_to_cartesia_language(language: Language) -> str | None:
     match language:
+        case Language.DE:
+            return "de"
         case Language.EN:
             return "en"
         case Language.ES:
             return "es"
+        case Language.FR:
+            return "fr"
+        case Language.JA:
+            return "ja"
+        case Language.PT:
+            return "pt"
+        case Language.ZH:
+            return "zh"
     return None
 
 

src/pipecat/transcriptions/language.py

@@ -19,5 +19,46 @@ else:
 
 
 class Language(StrEnum):
-    EN = "en"
-    ES = "es"
+    BG = "bg"            # Bulgarian
+    CA = "ca"            # Catalan
+    ZH = "zh"            # Chinese simplified
+    ZH_TW = "zh-TW"      # Chinese traditional
+    CS = "cs"            # Czech
+    DA = "da"            # Danish
+    NL = "nl"            # Dutch
+    EN = "en"            # English
+    EN_US = "en-US"      # English (USA)
+    EN_AU = "en-AU"      # English (Australia)
+    EN_GB = "en-GB"      # English (Great Britain)
+    EN_NZ = "en-NZ"      # English (New Zealand)
+    EN_IN = "en-IN"      # English (India)
+    ET = "et"            # Estonian
+    FI = "fi"            # Finnish
+    NL_BE = "nl-BE"      # Flemmish
+    FR = "fr"            # French
+    FR_CA = "fr-CA"      # French (Canada)
+    DE = "de"            # German
+    DE_CH = "de-CH"      # German (Switzerland)
+    EL = "el"            # Greek
+    HI = "hi"            # Hindi
+    HU = "hu"            # Hungarian
+    ID = "id"            # Indonesian
+    IT = "it"            # Italian
+    JA = "ja"            # Japanese
+    KO = "ko"            # Korean
+    LV = "lv"            # Latvian
+    LT = "lt"            # Lithuanian
+    MS = "ms"            # Malay
+    NO = "no"            # Norwegian
+    PL = "pl"            # Polish
+    PT = "pt"            # Portuguese
+    PT_BR = "pt-BR"      # Portuguese (Brazil)
+    RO = "ro"            # Romanian
+    RU = "ru"            # Russian
+    SK = "sk"            # Slovak
+    ES = "es"            # Spanish
+    SV = "sv"            # Swedish
+    TH = "th"            # Thai
+    TR = "tr"            # Turkish
+    UK = "uk"            # Ukrainian
+    VI = "vi"            # Vietnamese

src/pipecat/transports/services/daily.py

@@ -747,15 +747,6 @@ class DailyOutputTransport(BaseOutputTransport):
         await self._client.write_frame_to_camera(frame)
 
 
-def daily_language_to_language(language: str) -> Language | None:
-    match language:
-        case "en":
-            return Language.EN
-        case "es":
-            return Language.ES
-    return None
-
-
 class DailyTransport(BaseTransport):
 
     def __init__(
@@ -962,7 +953,7 @@ class DailyTransport(BaseTransport):
         is_final = message["rawResponse"]["is_final"]
         try:
             language = message["rawResponse"]["channel"]["alternatives"][0]["languages"][0]
-            language = daily_language_to_language(language)
+            language = Language(language)
         except KeyError:
             language = None
         if is_final: