--- title: "Initiate a new live job" method: POST path: "/v2/live" tags: ["Live V2"] --- # Initiate a new live job `POST /v2/live` ## Query parameters - `region` 'us-west' | 'eu-west' ## Request body - StreamingRequest - `encoding` 'wav/pcm' | 'wav/alaw' | 'wav/ulaw' — The encoding format of the audio stream. Supported formats: - PCM: 8, 16, 24, and 32 bits - A-law: 8 bits - μ-law: 8 bits Note: No need to add WAV headers to raw audio as the API supports both formats. - `bit_depth` 8 | 16 | 24 | 32 — The bit depth of the audio stream - `sample_rate` 8000 | 16000 | 32000 | 44100 | 48000 — The sample rate of the audio stream - `channels` integer — The number of channels of the audio stream - `custom_metadata` object — Custom metadata you can attach to this live transcription - `model` 'solaria-1' — The model used to process the audio. "solaria-1" is used by default. - `endpointing` number — The endpointing duration in seconds. Endpointing is the duration of silence which will cause an utterance to be considered as finished - `maximum_duration_without_endpointing` number — The maximum duration in seconds without endpointing. If endpointing is not detected after this duration, current utterance will be considered as finished - `language_config` LanguageConfig - `languages` TranscriptionLanguageCodeEnum[] — If one language is set, it will be used for the transcription. Otherwise, language will be auto-detected by the model. - `code_switching` boolean — If true, language will be auto-detected on each utterance. Otherwise, language will be auto-detected on first utterance and then used for the rest of the transcription. If one language is set, this option will be ignored. - `pre_processing` PreProcessingConfig - `audio_enhancer` boolean — If true, apply pre-processing to the audio stream to enhance the quality. - `speech_threshold` number — Sensitivity configuration for Speech Threshold. A value close to 1 will apply stricter thresholds, making it less likely to detect background sounds as speech. - `realtime_processing` RealtimeProcessingConfig - `custom_vocabulary` boolean — If true, enable custom vocabulary for the transcription. - `custom_vocabulary_config` CustomVocabularyConfigDTO - `vocabulary` union[], required — Specific vocabulary list to feed the transcription model with. Each item can be a string or an object with the following properties: value, intensity, pronunciations, language. - union - CustomVocabularyEntryDTO - `value` string, required — The text used to replace in the transcription. - `intensity` number — The global intensity of the feature. - `pronunciations` string[] — The pronunciations used in the transcription. - `language` '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' | 'yi' | 'yo' | 'zh' — Specify the language in which it will be pronounced when sound comparison occurs. Default to transcription language. - string - `default_intensity` number — Default intensity for the custom vocabulary - `custom_spelling` boolean — If true, enable custom spelling for the transcription. - `custom_spelling_config` CustomSpellingConfigDTO - `spelling_dictionary` object, required — The list of spelling applied on the audio transcription - `translation` boolean — If true, enable translation for the transcription - `translation_config` TranslationConfigDTO - `target_languages` TranslationLanguageCodeEnum[], required — Target language in `iso639-1` format you want the transcription translated to - `model` 'base' | 'batch' | 'enhanced' — Model you want the translation model to use to translate - `match_original_utterances` boolean — Align translated utterances with the original ones - `lipsync` boolean — Whether to apply lipsync to the translated transcription. - `context_adaptation` boolean — Enables or disables context-aware translation features that allow the model to adapt translations based on provided context. - `context` string — Context information to improve translation accuracy - `informal` boolean — Forces the translation to use informal language forms when available in the target language. - `named_entity_recognition` boolean — If true, enable named entity recognition for the transcription. - `sentiment_analysis` boolean — If true, enable sentiment analysis for the transcription. - `post_processing` PostProcessingConfig - `summarization` boolean — If true, generates summarization for the whole transcription. - `summarization_config` SummarizationConfigDTO - `type` 'general' | 'bullet_points' | 'concise' — The type of summarization to apply - `chapterization` boolean — If true, generates chapters for the whole transcription. - `messages_config` MessagesConfig - `receive_partial_transcripts` boolean — If true, partial transcript will be sent to websocket. - `receive_final_transcripts` boolean — If true, final transcript will be sent to websocket. - `receive_speech_events` boolean — If true, begin and end speech events will be sent to websocket. - `receive_pre_processing_events` boolean — If true, pre-processing events will be sent to websocket. - `receive_realtime_processing_events` boolean — If true, realtime processing events will be sent to websocket. - `receive_post_processing_events` boolean — If true, post-processing events will be sent to websocket. - `receive_acknowledgments` boolean — If true, acknowledgments will be sent to websocket. - `receive_errors` boolean — If true, errors will be sent to websocket. - `receive_lifecycle_events` boolean — If true, lifecycle events will be sent to websocket. - `callback` boolean — If true, messages will be sent to configured url. - `callback_config` CallbackConfig - `url` string, uri — URL on which we will do a `POST` request with configured messages - `receive_partial_transcripts` boolean — If true, partial transcript will be sent to the defined callback. - `receive_final_transcripts` boolean — If true, final transcript will be sent to the defined callback. - `receive_speech_events` boolean — If true, begin and end speech events will be sent to the defined callback. - `receive_pre_processing_events` boolean — If true, pre-processing events will be sent to the defined callback. - `receive_realtime_processing_events` boolean — If true, realtime processing events will be sent to the defined callback. - `receive_post_processing_events` boolean — If true, post-processing events will be sent to the defined callback. - `receive_acknowledgments` boolean — If true, acknowledgments will be sent to the defined callback. - `receive_errors` boolean — If true, errors will be sent to the defined callback. - `receive_lifecycle_events` boolean — If true, lifecycle events will be sent to the defined callback. ## Response `201` The live job has been initiated - InitStreamingResponse - `id` string, uuid, required — Id of the job - `created_at` string, date-time, required — Creation date - `url` string, uri, required — The websocket url to connect to for sending audio data. The url will contain the temporary token to authenticate the session. ## Other responses - `400` — Something is wrong with the request - `401` — You don't have the permissions to initiate a new live job - `422` — The parameters you gave are incorrect --- [API](https://skmtc.net/gladia/apis/gladia-control-api.md) · [All operations](https://skmtc.net/gladia/apis/gladia-control-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/gladia/gladia-control-api/revisions/8ec9ebfee489/schema)