Add ElevenLabsSTTService

CHANGELOG.md

@@ -9,8 +9,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
-- Added a peer connection monitor to the `SmallWebRTCConnection` that 
+- Added `ElevenLabsSTTService` for speech-to-text transcription.
-  automatically disconnects if the connection fails to establish within 
+
+- Added a peer connection monitor to the `SmallWebRTCConnection` that
+  automatically disconnects if the connection fails to establish within
   the timeout (1 minute by default).
 
 - Added memory cleanup improvements to reduce memory peaks.

README.md

@@ -79,7 +79,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 
 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                          |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                    |
 | LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                          |
 | Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
 | Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |

examples/foundational/07d-interruptible-elevenlabs-http.py

@@ -24,6 +24,7 @@ from pipecat.processors.aggregators.llm_response_universal import LLMContextAggr
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
 from pipecat.services.deepgram.stt import DeepgramSTTService
+from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
 from pipecat.services.elevenlabs.tts import ElevenLabsHttpTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -63,7 +64,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = ElevenLabsSTTService(
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            aiohttp_session=session,
+        )
 
         tts = ElevenLabsHttpTTSService(
             api_key=os.getenv("ELEVENLABS_API_KEY", ""),

examples/foundational/13k-elevenlabs-transcription.py

@@ -0,0 +1,89 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import os
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.runner.types import RunnerArguments
+from pipecat.runner.utils import create_transport
+from pipecat.services.elevenlabs.stt import ElevenLabsSTTService
+from pipecat.transports.base_transport import BaseTransport, TransportParams
+from pipecat.transports.daily.transport import DailyParams
+from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
+
+load_dotenv(override=True)
+
+
+class TranscriptionLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+        # Push all frames through
+        await self.push_frame(frame, direction)
+
+
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()
+    ),
+    "webrtc": lambda: TransportParams(audio_in_enabled=True, vad_analyzer=SileroVADAnalyzer()),
+}
+
+
+async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
+    logger.info(f"Starting bot")
+
+    async with aiohttp.ClientSession() as session:
+        stt = ElevenLabsSTTService(
+            api_key=os.getenv("ELEVENLABS_API_KEY"),
+            aiohttp_session=session,
+        )
+
+        tl = TranscriptionLogger()
+
+        pipeline = Pipeline([transport.input(), stt, tl])
+
+        task = PipelineTask(
+            pipeline,
+            idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
+        )
+
+        @transport.event_handler("on_client_disconnected")
+        async def on_client_disconnected(transport, client):
+            logger.info(f"Client disconnected")
+            await task.cancel()
+
+        runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
+
+        await runner.run(task)
+
+
+async def bot(runner_args: RunnerArguments):
+    """Main bot entry point compatible with Pipecat Cloud."""
+    transport = await create_transport(runner_args, transport_params)
+    await run_bot(transport, runner_args)
+
+
+if __name__ == "__main__":
+    from pipecat.runner.run import main
+
+    main()

src/pipecat/services/elevenlabs/stt.py

@@ -0,0 +1,339 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""ElevenLabs speech-to-text service implementation.
+
+This module provides integration with ElevenLabs' Speech-to-Text API for transcription
+using segmented audio processing. The service uploads audio files and receives
+transcription results directly.
+"""
+
+import io
+from typing import AsyncGenerator, Optional
+
+import aiohttp
+from loguru import logger
+from pydantic import BaseModel
+
+from pipecat.frames.frames import ErrorFrame, Frame, TranscriptionFrame
+from pipecat.services.stt_service import SegmentedSTTService
+from pipecat.transcriptions.language import Language
+from pipecat.utils.time import time_now_iso8601
+from pipecat.utils.tracing.service_decorators import traced_stt
+
+
+def language_to_elevenlabs_language(language: Language) -> Optional[str]:
+    """Convert a Language enum to ElevenLabs language code.
+
+    Source:
+        https://elevenlabs.io/docs/capabilities/speech-to-text
+
+    Args:
+        language: The Language enum value to convert.
+
+    Returns:
+        The corresponding ElevenLabs language code, or None if not supported.
+    """
+    BASE_LANGUAGES = {
+        Language.AF: "afr",  # Afrikaans
+        Language.AM: "amh",  # Amharic
+        Language.AR: "ara",  # Arabic
+        Language.HY: "hye",  # Armenian
+        Language.AS: "asm",  # Assamese
+        Language.AST: "ast",  # Asturian
+        Language.AZ: "aze",  # Azerbaijani
+        Language.BE: "bel",  # Belarusian
+        Language.BN: "ben",  # Bengali
+        Language.BS: "bos",  # Bosnian
+        Language.BG: "bul",  # Bulgarian
+        Language.MY: "mya",  # Burmese
+        Language.YUE: "yue",  # Cantonese
+        Language.CA: "cat",  # Catalan
+        Language.CEB: "ceb",  # Cebuano
+        Language.NY: "nya",  # Chichewa
+        Language.HR: "hrv",  # Croatian
+        Language.CS: "ces",  # Czech
+        Language.DA: "dan",  # Danish
+        Language.NL: "nld",  # Dutch
+        Language.EN: "eng",  # English
+        Language.ET: "est",  # Estonian
+        Language.FIL: "fil",  # Filipino
+        Language.FI: "fin",  # Finnish
+        Language.FR: "fra",  # French
+        Language.FF: "ful",  # Fulah
+        Language.GL: "glg",  # Galician
+        Language.LG: "lug",  # Ganda
+        Language.KA: "kat",  # Georgian
+        Language.DE: "deu",  # German
+        Language.EL: "ell",  # Greek
+        Language.GU: "guj",  # Gujarati
+        Language.HA: "hau",  # Hausa
+        Language.HE: "heb",  # Hebrew
+        Language.HI: "hin",  # Hindi
+        Language.HU: "hun",  # Hungarian
+        Language.IS: "isl",  # Icelandic
+        Language.IG: "ibo",  # Igbo
+        Language.ID: "ind",  # Indonesian
+        Language.GA: "gle",  # Irish
+        Language.IT: "ita",  # Italian
+        Language.JA: "jpn",  # Japanese
+        Language.JV: "jav",  # Javanese
+        Language.KEA: "kea",  # Kabuverdianu
+        Language.KN: "kan",  # Kannada
+        Language.KK: "kaz",  # Kazakh
+        Language.KM: "khm",  # Khmer
+        Language.KO: "kor",  # Korean
+        Language.KU: "kur",  # Kurdish
+        Language.KY: "kir",  # Kyrgyz
+        Language.LO: "lao",  # Lao
+        Language.LV: "lav",  # Latvian
+        Language.LN: "lin",  # Lingala
+        Language.LT: "lit",  # Lithuanian
+        Language.LUO: "luo",  # Luo
+        Language.LB: "ltz",  # Luxembourgish
+        Language.MK: "mkd",  # Macedonian
+        Language.MS: "msa",  # Malay
+        Language.ML: "mal",  # Malayalam
+        Language.MT: "mlt",  # Maltese
+        Language.ZH: "zho",  # Mandarin Chinese
+        Language.MI: "mri",  # Māori
+        Language.MR: "mar",  # Marathi
+        Language.MN: "mon",  # Mongolian
+        Language.NE: "nep",  # Nepali
+        Language.NSO: "nso",  # Northern Sotho
+        Language.NO: "nor",  # Norwegian
+        Language.OC: "oci",  # Occitan
+        Language.OR: "ori",  # Odia
+        Language.PS: "pus",  # Pashto
+        Language.FA: "fas",  # Persian
+        Language.PL: "pol",  # Polish
+        Language.PT: "por",  # Portuguese
+        Language.PA: "pan",  # Punjabi
+        Language.RO: "ron",  # Romanian
+        Language.RU: "rus",  # Russian
+        Language.SR: "srp",  # Serbian
+        Language.SN: "sna",  # Shona
+        Language.SD: "snd",  # Sindhi
+        Language.SK: "slk",  # Slovak
+        Language.SL: "slv",  # Slovenian
+        Language.SO: "som",  # Somali
+        Language.ES: "spa",  # Spanish
+        Language.SW: "swa",  # Swahili
+        Language.SV: "swe",  # Swedish
+        Language.TA: "tam",  # Tamil
+        Language.TG: "tgk",  # Tajik
+        Language.TE: "tel",  # Telugu
+        Language.TH: "tha",  # Thai
+        Language.TR: "tur",  # Turkish
+        Language.UK: "ukr",  # Ukrainian
+        Language.UMB: "umb",  # Umbundu
+        Language.UR: "urd",  # Urdu
+        Language.UZ: "uzb",  # Uzbek
+        Language.VI: "vie",  # Vietnamese
+        Language.CY: "cym",  # Welsh
+        Language.WO: "wol",  # Wolof
+        Language.XH: "xho",  # Xhosa
+        Language.ZU: "zul",  # Zulu
+    }
+
+    result = BASE_LANGUAGES.get(language)
+
+    # If not found in base languages, try to find the base language from a variant
+    if not result:
+        lang_str = str(language.value)
+        base_code = lang_str.split("-")[0].lower()
+        result = base_code if base_code in BASE_LANGUAGES.values() else None
+
+    return result
+
+
+class ElevenLabsSTTService(SegmentedSTTService):
+    """Speech-to-text service using ElevenLabs' file-based API.
+
+    This service uses ElevenLabs' Speech-to-Text API to perform transcription on audio
+    segments. It inherits from SegmentedSTTService to handle audio buffering and speech detection.
+    The service uploads audio files to ElevenLabs and receives transcription results directly.
+    """
+
+    class InputParams(BaseModel):
+        """Configuration parameters for ElevenLabs STT API.
+
+        Parameters:
+            language: Target language for transcription.
+            tag_audio_events: Whether to include audio events like (laughter), (coughing), in the transcription.
+        """
+
+        language: Optional[Language] = None
+        tag_audio_events: bool = True
+
+    def __init__(
+        self,
+        *,
+        api_key: str,
+        aiohttp_session: aiohttp.ClientSession,
+        base_url: str = "https://api.elevenlabs.io",
+        model: str = "scribe_v1",
+        sample_rate: Optional[int] = None,
+        params: Optional[InputParams] = None,
+        **kwargs,
+    ):
+        """Initialize the ElevenLabs STT service.
+
+        Args:
+            api_key: ElevenLabs API key for authentication.
+            aiohttp_session: aiohttp ClientSession for HTTP requests.
+            base_url: Base URL for ElevenLabs API.
+            model: Model ID for transcription. Defaults to "scribe_v1".
+            sample_rate: Audio sample rate in Hz. If not provided, uses the pipeline's rate.
+            params: Configuration parameters for the STT service.
+            **kwargs: Additional arguments passed to SegmentedSTTService.
+        """
+        super().__init__(
+            sample_rate=sample_rate,
+            **kwargs,
+        )
+
+        params = params or ElevenLabsSTTService.InputParams()
+
+        self._api_key = api_key
+        self._base_url = base_url
+        self._session = aiohttp_session
+        self._model_id = model
+        self._tag_audio_events = params.tag_audio_events
+
+        self._settings = {
+            "language": self.language_to_service_language(params.language)
+            if params.language
+            else "eng",
+        }
+
+    def can_generate_metrics(self) -> bool:
+        """Check if the service can generate processing metrics.
+
+        Returns:
+            True, as ElevenLabs STT service supports metrics generation.
+        """
+        return True
+
+    def language_to_service_language(self, language: Language) -> Optional[str]:
+        """Convert a Language enum to ElevenLabs service-specific language code.
+
+        Args:
+            language: The language to convert.
+
+        Returns:
+            The ElevenLabs-specific language code, or None if not supported.
+        """
+        return language_to_elevenlabs_language(language)
+
+    async def set_language(self, language: Language):
+        """Set the transcription language.
+
+        Args:
+            language: The language to use for speech-to-text transcription.
+        """
+        logger.info(f"Switching STT language to: [{language}]")
+        self._settings["language"] = self.language_to_service_language(language)
+
+    async def set_model(self, model: str):
+        """Set the STT model.
+
+        Args:
+            model: The model name to use for transcription.
+
+        Note:
+            ElevenLabs STT API does not currently support model selection.
+            This method is provided for interface compatibility.
+        """
+        await super().set_model(model)
+        logger.info(f"Model setting [{model}] noted, but ElevenLabs STT uses default model")
+
+    async def _transcribe_audio(self, audio_data: bytes) -> dict:
+        """Upload audio data to ElevenLabs and get transcription result.
+
+        Args:
+            audio_data: Raw audio bytes in WAV format.
+
+        Returns:
+            The transcription result data.
+
+        Raises:
+            Exception: If transcription fails or returns an error.
+        """
+        url = f"{self._base_url}/v1/speech-to-text"
+        headers = {"xi-api-key": self._api_key}
+
+        # Create form data with the audio file
+        data = aiohttp.FormData()
+        data.add_field(
+            "file",
+            io.BytesIO(audio_data),
+            filename="audio.wav",
+            content_type="audio/x-wav",
+        )
+
+        # Add required model_id, language_code, and tag_audio_events
+        data.add_field("model_id", self._model_id)
+        data.add_field("language_code", self._settings["language"])
+        data.add_field("tag_audio_events", str(self._tag_audio_events).lower())
+
+        async with self._session.post(url, data=data, headers=headers) as response:
+            if response.status != 200:
+                error_text = await response.text()
+                logger.error(f"ElevenLabs transcription error: {error_text}")
+                raise Exception(f"Transcription failed with status {response.status}: {error_text}")
+
+            result = await response.json()
+            return result
+
+    @traced_stt
+    async def _handle_transcription(
+        self, transcript: str, is_final: bool, language: Optional[str] = None
+    ):
+        """Handle a transcription result with tracing."""
+        await self.stop_ttfb_metrics()
+        await self.stop_processing_metrics()
+
+    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
+        """Transcribe an audio segment using ElevenLabs' STT API.
+
+        Args:
+            audio: Raw audio bytes in WAV format (already converted by base class).
+
+        Yields:
+            Frame: TranscriptionFrame containing the transcribed text, or ErrorFrame on failure.
+
+        Note:
+            The audio is already in WAV format from the SegmentedSTTService.
+            Only non-empty transcriptions are yielded.
+        """
+        try:
+            await self.start_processing_metrics()
+            await self.start_ttfb_metrics()
+
+            # Upload audio and get transcription result directly
+            result = await self._transcribe_audio(audio)
+
+            # Extract transcription text
+            text = result.get("text", "").strip()
+            if text:
+                # Use the language_code returned by the API
+                detected_language = result.get("language_code", "eng")
+
+                await self._handle_transcription(text, True, detected_language)
+                logger.debug(f"Transcription: [{text}]")
+
+                yield TranscriptionFrame(
+                    text,
+                    self._user_id,
+                    time_now_iso8601(),
+                    detected_language,
+                    result=result,
+                )
+
+        except Exception as e:
+            logger.error(f"ElevenLabs STT error: {e}")
+            yield ErrorFrame(f"ElevenLabs STT error: {str(e)}")

src/pipecat/transcriptions/language.py

@@ -68,6 +68,9 @@ class Language(StrEnum):
     AS = "as"
     AS_IN = "as-IN"
 
+    # Asturian
+    AST = "ast"
+
     # Azerbaijani
     AZ = "az"
     AZ_AZ = "az-AZ"
@@ -101,6 +104,9 @@ class Language(StrEnum):
     CA = "ca"
     CA_ES = "ca-ES"
 
+    # Cebuano
+    CEB = "ceb"
+
     # Mandarin Chinese
     CMN = "cmn"
     CMN_CN = "cmn-CN"
@@ -185,6 +191,9 @@ class Language(StrEnum):
     FA = "fa"
     FA_IR = "fa-IR"
 
+    # Fulah
+    FF = "ff"
+
     # Finnish
     FI = "fi"
     FI_FI = "fi-FI"
@@ -251,6 +260,9 @@ class Language(StrEnum):
     ID = "id"
     ID_ID = "id-ID"
 
+    # Igbo
+    IG = "ig"
+
     # Icelandic
     IS = "is"
     IS_IS = "is-IS"
@@ -279,6 +291,9 @@ class Language(StrEnum):
     KA = "ka"
     KA_GE = "ka-GE"
 
+    # Kabuverdianu
+    KEA = "kea"
+
     # Kazakh
     KK = "kk"
     KK_KZ = "kk-KZ"
@@ -295,6 +310,13 @@ class Language(StrEnum):
     KO = "ko"
     KO_KR = "ko-KR"
 
+    # Kurdish
+    KU = "ku"
+
+    # Kyrgyz
+    KY = "ky"
+    KY_KG = "ky-KG"
+
     # Latin
     LA = "la"
 
@@ -312,6 +334,12 @@ class Language(StrEnum):
     LT = "lt"
     LT_LT = "lt-LT"
 
+    # Ganda
+    LG = "lg"
+
+    # Luo
+    LUO = "luo"
+
     # Latvian
     LV = "lv"
     LV_LV = "lv-LV"
@@ -366,6 +394,12 @@ class Language(StrEnum):
     NL_BE = "nl-BE"
     NL_NL = "nl-NL"
 
+    # Northern Sotho
+    NSO = "nso"
+
+    # Chichewa
+    NY = "ny"
+
     # Occitan
     OC = "oc"
 
@@ -484,6 +518,9 @@ class Language(StrEnum):
     UK = "uk"
     UK_UA = "uk-UA"
 
+    # Umbundu
+    UMB = "umb"
+
     # Urdu
     UR = "ur"
     UR_IN = "ur-IN"
@@ -497,6 +534,9 @@ class Language(StrEnum):
     VI = "vi"
     VI_VN = "vi-VN"
 
+    # Wolof
+    WO = "wo"
+
     # Wu Chinese
     WUU = "wuu"
     WUU_CN = "wuu-CN"
@@ -507,7 +547,7 @@ class Language(StrEnum):
     # Yoruba
     YO = "yo"
 
-    # Yue Chinese
+    # Yue Chinese (Cantonese)
     YUE = "yue"
     YUE_CN = "yue-CN"