apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-07-07 11:02:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add google stt and tts. add folders to organize agents

Browse source
This commit is contained in:
Abhishek Kumar 2026-05-22 14:36:50 +05:30
parent 21951eca18
commit ad2fa07058
52 changed files with 3412 additions and 621 deletions
Download patch file Download diff file Expand all files Collapse all files

49
api/services/configuration/options/__init__.py Normal file
View file

@ -0,0 +1,49 @@
from .deepgram import DEEPGRAM_LANGUAGES, DEEPGRAM_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_STT_MODELS,
SARVAM_TTS_MODELS,
SARVAM_V2_VOICES,
SARVAM_V3_VOICES,
)
from .speechmatics import SPEECHMATICS_STT_LANGUAGES
__all__ = [
"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_STT_MODELS",
"SARVAM_TTS_MODELS",
"SARVAM_V2_VOICES",
"SARVAM_V3_VOICES",
"SPEECHMATICS_STT_LANGUAGES",
]

84
api/services/configuration/options/deepgram.py Normal file
View file

@ -0,0 +1,84 @@
DEEPGRAM_STT_MODELS = ("nova-3-general", "flux-general-en", "flux-general-multi")
DEEPGRAM_LANGUAGES = (
"multi",
"ar",
"ar-AE",
"ar-SA",
"ar-QA",
"ar-KW",
"ar-SY",
"ar-LB",
"ar-PS",
"ar-JO",
"ar-EG",
"ar-SD",
"ar-TD",
"ar-MA",
"ar-DZ",
"ar-TN",
"ar-IQ",
"ar-IR",
"be",
"bn",
"bs",
"bg",
"ca",
"cs",
"da",
"da-DK",
"de",
"de-CH",
"el",
"en",
"en-US",
"en-AU",
"en-GB",
"en-IN",
"en-NZ",
"es",
"es-419",
"et",
"fa",
"fi",
"fr",
"fr-CA",
"he",
"hi",
"hr",
"hu",
"id",
"it",
"ja",
"kn",
"ko",
"ko-KR",
"lt",
"lv",
"mk",
"mr",
"ms",
"nl",
"nl-BE",
"no",
"pl",
"pt",
"pt-BR",
"pt-PT",
"ro",
"ru",
"sk",
"sl",
"sr",
"sv",
"sv-SE",
"ta",
"te",
"th",
"tl",
"tr",
"uk",
"ur",
"vi",
"zh-CN",
"zh-TW",
)

103
api/services/configuration/options/gladia.py Normal file
View file

@ -0,0 +1,103 @@
GLADIA_STT_MODELS = ("solaria-1",)
GLADIA_STT_LANGUAGES = (
"af",
"am",
"ar",
"as",
"az",
"ba",
"be",
"bg",
"bn",
"bo",
"br",
"bs",
"ca",
"cs",
"cy",
"da",
"de",
"el",
"en",
"es",
"et",
"eu",
"fa",
"fi",
"fo",
"fr",
"gl",
"gu",
"ha",
"haw",
"he",
"hi",
"hr",
"ht",
"hu",
"hy",
"id",
"is",
"it",
"ja",
"jw",
"ka",
"kk",
"km",
"kn",
"ko",
"la",
"lb",
"ln",
"lo",
"lt",
"lv",
"mg",
"mi",
"mk",
"ml",
"mn",
"mr",
"ms",
"mt",
"my",
"ne",
"nl",
"nn",
"no",
"oc",
"pa",
"pl",
"ps",
"pt",
"ro",
"ru",
"sa",
"sd",
"si",
"sk",
"sl",
"sn",
"so",
"sq",
"sr",
"su",
"sv",
"sw",
"ta",
"te",
"tg",
"th",
"tk",
"tl",
"tr",
"tt",
"uk",
"ur",
"uz",
"vi",
"wo",
"yi",
"yo",
"zh",
)

273
api/services/configuration/options/google.py Normal file
View file

@ -0,0 +1,273 @@
GOOGLE_MODELS = (
"gemini-2.0-flash",
"gemini-2.0-flash-lite",
"gemini-2.5-flash",
"gemini-2.5-flash-lite",
)
GOOGLE_REALTIME_MODELS = ("gemini-3.1-flash-live-preview",)
GOOGLE_REALTIME_VOICES = ("Puck", "Charon", "Kore", "Fenrir", "Aoede")
GOOGLE_REALTIME_LANGUAGES = (
"ar",
"bn",
"de",
"en",
"es",
"fr",
"gu",
"hi",
"id",
"it",
"ja",
"kn",
"ko",
"ml",
"mr",
"nl",
"pl",
"pt",
"ru",
"ta",
"te",
"th",
"tr",
"vi",
"zh",
)
GOOGLE_VERTEX_REALTIME_MODELS = ("google/gemini-live-2.5-flash-native-audio",)
GOOGLE_VERTEX_REALTIME_VOICES = GOOGLE_REALTIME_VOICES
GOOGLE_VERTEX_REALTIME_LANGUAGES = GOOGLE_REALTIME_LANGUAGES
GOOGLE_STT_MODELS = ("latest_long", "latest_short", "chirp_3")
# Docs-derived from Google Cloud Speech-to-Text V2 supported languages.
GOOGLE_STT_LANGUAGES = (
"af-ZA",
"am-ET",
"ar-AE",
"ar-BH",
"ar-DZ",
"ar-EG",
"ar-IL",
"ar-IQ",
"ar-JO",
"ar-KW",
"ar-LB",
"ar-MA",
"ar-MR",
"ar-OM",
"ar-PS",
"ar-QA",
"ar-SA",
"ar-SY",
"ar-TN",
"ar-XA",
"ar-YE",
"as-IN",
"ast-ES",
"az-AZ",
"be-BY",
"bg-BG",
"bn-BD",
"bn-IN",
"bs-BA",
"ca-ES",
"ceb-PH",
"ckb-IQ",
"cmn-Hans-CN",
"cmn-Hant-TW",
"cs-CZ",
"cy-GB",
"da-DK",
"de-AT",
"de-CH",
"de-DE",
"el-GR",
"en-AU",
"en-GB",
"en-HK",
"en-IE",
"en-IN",
"en-NZ",
"en-PH",
"en-PK",
"en-SG",
"en-US",
"es-419",
"es-AR",
"es-BO",
"es-CL",
"es-CO",
"es-CR",
"es-DO",
"es-EC",
"es-ES",
"es-GT",
"es-HN",
"es-MX",
"es-NI",
"es-PA",
"es-PE",
"es-PR",
"es-SV",
"es-US",
"es-UY",
"es-VE",
"et-EE",
"eu-ES",
"fa-IR",
"ff-SN",
"fi-FI",
"fil-PH",
"fr-BE",
"fr-CA",
"fr-CH",
"fr-FR",
"ga-IE",
"gl-ES",
"gu-IN",
"ha-NG",
"hi-IN",
"hr-HR",
"hu-HU",
"hy-AM",
"id-ID",
"ig-NG",
"is-IS",
"it-CH",
"it-IT",
"iw-IL",
"ja-JP",
"jv-ID",
"ka-GE",
"kam-KE",
"kea-CV",
"kk-KZ",
"km-KH",
"kn-IN",
"ko-KR",
"ky-KG",
"lb-LU",
"lg-UG",
"ln-CD",
"lo-LA",
"lt-LT",
"luo-KE",
"lv-LV",
"mi-NZ",
"mk-MK",
"ml-IN",
"mn-MN",
"mr-IN",
"ms-MY",
"mt-MT",
"my-MM",
"ne-NP",
"nl-BE",
"nl-NL",
"no-NO",
"nso-ZA",
"ny-MW",
"oc-FR",
"om-ET",
"or-IN",
"pa-Guru-IN",
"pl-PL",
"ps-AF",
"pt-BR",
"pt-PT",
"ro-RO",
"ru-RU",
"rup-BG",
"rw-RW",
"sd-IN",
"si-LK",
"sk-SK",
"sl-SI",
"sn-ZW",
"so-SO",
"sq-AL",
"sr-RS",
"ss-Latn-ZA",
"st-ZA",
"su-ID",
"sv-SE",
"sw",
"sw-KE",
"ta-IN",
"te-IN",
"tg-TJ",
"th-TH",
"tn-Latn-ZA",
"tr-TR",
"ts-ZA",
"uk-UA",
"umb-AO",
"ur-PK",
"uz-UZ",
"ve-ZA",
"vi-VN",
"wo-SN",
"xh-ZA",
"yo-NG",
"yue-Hant-HK",
"zu-ZA",
)
GOOGLE_TTS_MODELS = ("chirp_3_hd",)
GOOGLE_TTS_VOICES = ("en-US-Chirp3-HD-Charon",)
GOOGLE_TTS_LANGUAGES = (
"ar-XA",
"bn-IN",
"bg-BG",
"yue-HK",
"hr-HR",
"cs-CZ",
"da-DK",
"nl-BE",
"nl-NL",
"en-AU",
"en-IN",
"en-GB",
"en-US",
"et-EE",
"fi-FI",
"fr-CA",
"fr-FR",
"de-DE",
"el-GR",
"gu-IN",
"he-IL",
"hi-IN",
"hu-HU",
"id-ID",
"it-IT",
"ja-JP",
"kn-IN",
"ko-KR",
"lv-LV",
"lt-LT",
"ml-IN",
"cmn-CN",
"mr-IN",
"nb-NO",
"pl-PL",
"pt-BR",
"pa-IN",
"ro-RO",
"ru-RU",
"sr-RS",
"sk-SK",
"sl-SI",
"es-ES",
"es-US",
"sw-KE",
"sv-SE",
"ta-IN",
"te-IN",
"th-TH",
"tr-TR",
"uk-UA",
"ur-IN",
"vi-VN",
)

66
api/services/configuration/options/sarvam.py Normal file
View file

@ -0,0 +1,66 @@
SARVAM_TTS_MODELS = ("bulbul:v2", "bulbul:v3")
SARVAM_V2_VOICES = (
"anushka",
"manisha",
"vidya",
"arya",
"abhilash",
"karun",
"hitesh",
)
SARVAM_V3_VOICES = (
"shubh",
"aditya",
"ritu",
"priya",
"neha",
"rahul",
"pooja",
"rohan",
"simran",
"kavya",
"amit",
"dev",
"ishita",
"shreya",
"ratan",
"varun",
"manan",
"sumit",
"roopa",
"kabir",
"aayan",
"ashutosh",
"advait",
"amelia",
"sophia",
"anand",
"tanya",
"tarun",
"sunny",
"mani",
"gokul",
"vijay",
"shruti",
"suhani",
"mohit",
"kavitha",
"rehan",
"soham",
"rupali",
)
SARVAM_LANGUAGES = (
"bn-IN",
"en-IN",
"gu-IN",
"hi-IN",
"kn-IN",
"ml-IN",
"mr-IN",
"od-IN",
"pa-IN",
"ta-IN",
"te-IN",
"as-IN",
)
SARVAM_STT_MODELS = ("saarika:v2.5", "saaras:v2")

63
api/services/configuration/options/speechmatics.py Normal file
View file

@ -0,0 +1,63 @@
SPEECHMATICS_STT_LANGUAGES = (
"ar",
"ar_en",
"ba",
"eu",
"be",
"bn",
"bg",
"yue",
"ca",
"hr",
"cs",
"da",
"nl",
"en",
"eo",
"et",
"fi",
"fr",
"gl",
"de",
"el",
"he",
"hi",
"hu",
"id",
"ia",
"ga",
"it",
"ja",
"ko",
"lv",
"lt",
"ms",
"en_ms",
"mt",
"cmn",
"cmn_en",
"cmn_en_ms_ta",
"mr",
"mn",
"no",
"fa",
"pl",
"pt",
"ro",
"ru",
"sk",
"sl",
"es",
"sw",
"sv",
"tl",
"ta",
"en_ta",
"th",
"tr",
"uk",
"ur",
"ug",
"vi",
"cy",
)