{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "#/components/schemas/AzureSpeechTranscriber",
"title": "AzureSpeechTranscriber",
"type": "object",
"properties": {
"provider": {
"type": "string",
"description": "This is the transcription provider that will be used.",
"enum": [
"azure"
]
},
"language": {
"type": "string",
"description": "This is the language that will be set for the transcription. The list of languages Azure supports can be found here: https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=stt",
"enum": [
"af-ZA",
"am-ET",
"ar-AE",
"ar-BH",
"ar-DZ",
"ar-EG",
"ar-IL",
"ar-IQ",
"ar-JO",
"ar-KW",
"ar-LB",
"ar-LY",
"ar-MA",
"ar-OM",
"ar-PS",
"ar-QA",
"ar-SA",
"ar-SY",
"ar-TN",
"ar-YE",
"az-AZ",
"bg-BG",
"bn-IN",
"bs-BA",
"ca-ES",
"cs-CZ",
"cy-GB",
"da-DK",
"de-AT",
"de-CH",
"de-DE",
"el-GR",
"en-AU",
"en-CA",
"en-GB",
"en-GH",
"en-HK",
"en-IE",
"en-IN",
"en-KE",
"en-NG",
"en-NZ",
"en-PH",
"en-SG",
"en-TZ",
"en-US",
"en-ZA",
"es-AR",
"es-BO",
"es-CL",
"es-CO",
"es-CR",
"es-CU",
"es-DO",
"es-EC",
"es-ES",
"es-GQ",
"es-GT",
"es-HN",
"es-MX",
"es-NI",
"es-PA",
"es-PE",
"es-PR",
"es-PY",
"es-SV",
"es-US",
"es-UY",
"es-VE",
"et-EE",
"eu-ES",
"fa-IR",
"fi-FI",
"fil-PH",
"fr-BE",
"fr-CA",
"fr-CH",
"fr-FR",
"ga-IE",
"gl-ES",
"gu-IN",
"he-IL",
"hi-IN",
"hr-HR",
"hu-HU",
"hy-AM",
"id-ID",
"is-IS",
"it-CH",
"it-IT",
"ja-JP",
"jv-ID",
"ka-GE",
"kk-KZ",
"km-KH",
"kn-IN",
"ko-KR",
"lo-LA",
"lt-LT",
"lv-LV",
"mk-MK",
"ml-IN",
"mn-MN",
"mr-IN",
"ms-MY",
"mt-MT",
"my-MM",
"nb-NO",
"ne-NP",
"nl-BE",
"nl-NL",
"pa-IN",
"pl-PL",
"ps-AF",
"pt-BR",
"pt-PT",
"ro-RO",
"ru-RU",
"si-LK",
"sk-SK",
"sl-SI",
"so-SO",
"sq-AL",
"sr-RS",
"sv-SE",
"sw-KE",
"sw-TZ",
"ta-IN",
"te-IN",
"th-TH",
"tr-TR",
"uk-UA",
"ur-IN",
"uz-UZ",
"vi-VN",
"wuu-CN",
"yue-CN",
"zh-CN",
"zh-CN-shandong",
"zh-CN-sichuan",
"zh-HK",
"zh-TW",
"zu-ZA"
]
},
"segmentationStrategy": {
"type": "string",
"description": "Controls how phrase boundaries are detected, enabling either simple time/silence heuristics or more advanced semantic segmentation.",
"enum": [
"Default",
"Time",
"Semantic"
]
},
"segmentationSilenceTimeoutMs": {
"type": "number",
"description": "Duration of detected silence after which the service finalizes a phrase. Configure to adjust sensitivity to pauses in speech.",
"minimum": 100,
"maximum": 5000
},
"segmentationMaximumTimeMs": {
"type": "number",
"description": "Maximum duration a segment can reach before being cut off when using time-based segmentation.",
"minimum": 20000,
"maximum": 70000
},
"fallbackPlan": {
"description": "This is the plan for transcriber provider fallbacks in the event that the primary transcriber provider fails.",
"allOf": [
{
"$ref": "#/components/schemas/FallbackTranscriberPlan"
}
]
}
},
"required": [
"provider"
]
}