mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-07-13 11:22:14 +02:00
cfe1d3709a
* feat: add ElevenLabs realtime STT provider support (#512) Wire ElevenLabs scribe_v2_realtime into the STT registry and pipeline factory so BYOK transcribers can use the same provider already supported for TTS. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: address ElevenLabs STT review feedback for language, commits, and host Pass custom language codes through instead of defaulting to English, use ElevenLabs VAD commit strategy because Dograh VAD runs downstream of STT, and document hostname-only realtime base_url handling. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: preserve ElevenLabs STT endpoint port in realtime host parsing Use urlparse netloc instead of hostname so validated BYOK/proxy base URLs keep non-default ports when Pipecat builds the websocket endpoint. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: preserve ElevenLabs STT proxy path prefix and remove duplicate tests Include URL path segments in realtime host normalization for BYOK proxies and delete shadowed pytest definitions. Co-authored-by: Cursor <cursoragent@cursor.com> * fix: allow custom ElevenLabs model input * fix: normalize ElevenLabs websocket URLs --------- Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
107 lines
2.9 KiB
Python
107 lines
2.9 KiB
Python
from .azure import (
|
|
AZURE_EMBEDDING_MODELS,
|
|
AZURE_MODELS,
|
|
AZURE_REALTIME_API_VERSIONS,
|
|
AZURE_REALTIME_MODELS,
|
|
AZURE_REALTIME_VOICES,
|
|
AZURE_SPEECH_REGIONS,
|
|
AZURE_SPEECH_STT_LANGUAGES,
|
|
AZURE_SPEECH_TTS_LANGUAGES,
|
|
AZURE_SPEECH_TTS_VOICES,
|
|
)
|
|
from .cartesia import (
|
|
CARTESIA_INK_2_STT_LANGUAGES,
|
|
CARTESIA_INK_WHISPER_STT_LANGUAGES,
|
|
CARTESIA_STT_LANGUAGES,
|
|
CARTESIA_STT_MODELS,
|
|
)
|
|
from .deepgram import (
|
|
DEEPGRAM_FLUX_MODELS,
|
|
DEEPGRAM_FLUX_MULTILINGUAL_LANGUAGE_OPTIONS,
|
|
DEEPGRAM_FLUX_MULTILINGUAL_LANGUAGES,
|
|
DEEPGRAM_LANGUAGES,
|
|
DEEPGRAM_STT_MODELS,
|
|
)
|
|
from .elevenlabs import ELEVENLABS_STT_LANGUAGES, ELEVENLABS_STT_MODELS
|
|
from .gladia import GLADIA_STT_LANGUAGES, GLADIA_STT_MODELS
|
|
from .google import (
|
|
GOOGLE_MODELS,
|
|
GOOGLE_REALTIME_LANGUAGES,
|
|
GOOGLE_REALTIME_MODELS,
|
|
GOOGLE_REALTIME_VOICES,
|
|
GOOGLE_STT_LANGUAGES,
|
|
GOOGLE_STT_MODELS,
|
|
GOOGLE_TTS_LANGUAGES,
|
|
GOOGLE_TTS_MODELS,
|
|
GOOGLE_TTS_VOICES,
|
|
GOOGLE_VERTEX_REALTIME_LANGUAGES,
|
|
GOOGLE_VERTEX_REALTIME_MODELS,
|
|
GOOGLE_VERTEX_REALTIME_VOICES,
|
|
)
|
|
from .sarvam import (
|
|
SARVAM_LANGUAGES,
|
|
SARVAM_LLM_MODELS,
|
|
SARVAM_STT_LANGUAGES_V3,
|
|
SARVAM_STT_LANGUAGES_V25,
|
|
SARVAM_STT_MODELS,
|
|
SARVAM_TTS_MODELS,
|
|
SARVAM_V2_VOICES,
|
|
SARVAM_V3_VOICES,
|
|
)
|
|
from .smallest import (
|
|
SMALLEST_TTS_LANGUAGES,
|
|
SMALLEST_TTS_MODELS,
|
|
SMALLEST_TTS_PRO_VOICES,
|
|
SMALLEST_TTS_VOICES,
|
|
)
|
|
from .speechmatics import SPEECHMATICS_STT_LANGUAGES
|
|
|
|
__all__ = [
|
|
"AZURE_EMBEDDING_MODELS",
|
|
"AZURE_MODELS",
|
|
"AZURE_REALTIME_API_VERSIONS",
|
|
"AZURE_REALTIME_MODELS",
|
|
"AZURE_REALTIME_VOICES",
|
|
"AZURE_SPEECH_REGIONS",
|
|
"AZURE_SPEECH_STT_LANGUAGES",
|
|
"AZURE_SPEECH_TTS_LANGUAGES",
|
|
"AZURE_SPEECH_TTS_VOICES",
|
|
"CARTESIA_INK_2_STT_LANGUAGES",
|
|
"CARTESIA_INK_WHISPER_STT_LANGUAGES",
|
|
"CARTESIA_STT_LANGUAGES",
|
|
"CARTESIA_STT_MODELS",
|
|
"ELEVENLABS_STT_LANGUAGES",
|
|
"ELEVENLABS_STT_MODELS",
|
|
"DEEPGRAM_FLUX_MODELS",
|
|
"DEEPGRAM_FLUX_MULTILINGUAL_LANGUAGES",
|
|
"DEEPGRAM_FLUX_MULTILINGUAL_LANGUAGE_OPTIONS",
|
|
"DEEPGRAM_LANGUAGES",
|
|
"DEEPGRAM_STT_MODELS",
|
|
"GLADIA_STT_LANGUAGES",
|
|
"GLADIA_STT_MODELS",
|
|
"GOOGLE_MODELS",
|
|
"GOOGLE_REALTIME_LANGUAGES",
|
|
"GOOGLE_REALTIME_MODELS",
|
|
"GOOGLE_REALTIME_VOICES",
|
|
"GOOGLE_STT_LANGUAGES",
|
|
"GOOGLE_STT_MODELS",
|
|
"GOOGLE_TTS_LANGUAGES",
|
|
"GOOGLE_TTS_MODELS",
|
|
"GOOGLE_TTS_VOICES",
|
|
"GOOGLE_VERTEX_REALTIME_LANGUAGES",
|
|
"GOOGLE_VERTEX_REALTIME_MODELS",
|
|
"GOOGLE_VERTEX_REALTIME_VOICES",
|
|
"SARVAM_LANGUAGES",
|
|
"SARVAM_LLM_MODELS",
|
|
"SARVAM_STT_LANGUAGES_V25",
|
|
"SARVAM_STT_LANGUAGES_V3",
|
|
"SARVAM_STT_MODELS",
|
|
"SARVAM_TTS_MODELS",
|
|
"SARVAM_V2_VOICES",
|
|
"SARVAM_V3_VOICES",
|
|
"SMALLEST_TTS_LANGUAGES",
|
|
"SMALLEST_TTS_MODELS",
|
|
"SMALLEST_TTS_PRO_VOICES",
|
|
"SMALLEST_TTS_VOICES",
|
|
"SPEECHMATICS_STT_LANGUAGES",
|
|
]
|