AsrInput
Properties
| Name | Type | Required | Description |
|---|---|---|---|
| content_uri | str | ❌ | Publicly facing uri |
| encoding | AsrInputEncoding | ❌ | The encoding of the original audio |
| language_code | str | ❌ | Language spoken in the audio file. |
| source | str | ❌ | Source of the audio file eg: Phone, RingCentral, GoogleMeet, Zoom etc |
| audio_type | AsrInputAudioType | ❌ | Type of the audio |
| separate_speaker_per_channel | bool | ❌ | Indicates that the input audio is multi-channel and each channel has a separate speaker. |
| speaker_count | int | ❌ | Number of speakers in the file, omit parameter if unknown |
| speaker_ids | List[str] | ❌ | Optional set of speakers to be identified from the call. |
| enable_voice_activity_detection | bool | ❌ | Apply voice activity detection. |
| enable_punctuation | bool | ❌ | Enables Smart Punctuation API. |
| enable_speaker_diarization | bool | ❌ | Tags each word corresponding to the speaker. |
| speech_contexts | List[SpeechContextPhrasesInput] | ❌ | Indicates the words/phrases that will be used for boosting the transcript. This can help to boost accuracy for cases like Person Names, Company names etc. |
AsrInputEncoding
The encoding of the original audio
Properties
| Name | Type | Required | Description |
|---|---|---|---|
| MPEG | str | ✅ | "Mpeg" |
| MP4 | str | ✅ | "Mp4" |
| WAV | str | ✅ | "Wav" |
| WEBM | str | ✅ | "Webm" |
| WEBP | str | ✅ | "Webp" |
| AAC | str | ✅ | "Aac" |
| AVI | str | ✅ | "Avi" |
| OGG | str | ✅ | "Ogg" |
AsrInputAudioType
Type of the audio
Properties
| Name | Type | Required | Description |
|---|---|---|---|
| CALLCENTER | str | ✅ | "CallCenter" |
| MEETING | str | ✅ | "Meeting" |
| EARNINGSCALLS | str | ✅ | "EarningsCalls" |
| INTERVIEW | str | ✅ | "Interview" |
| PRESSCONFERENCE | str | ✅ | "PressConference" |
| VOICEMAIL | str | ✅ | "Voicemail" |
Build Your Own SDKs with liblab
Build developer friendly SDKs in minutes from your APIs