Sonartext Speech To Text
Pricing
Pay per event
Go to Apify Store
Sonartext Speech To Text
Under maintenanceSonarText Speech to Text Transcription Service
0.0 (0)
Pricing
Pay per event
1
2
2
Last modified
20 days ago
Pricing
Pay per event
SonarText Speech to Text Transcription Service
0.0 (0)
Pricing
Pay per event
1
2
2
Last modified
20 days ago
inputMethod
EnumRequired
How to provide the audio/video file
"file_upload": string"url": string"youtube": string"twitter": string"gdrive": string"s3": string
Default value of this property is "file_upload"
audioFile
stringOptional
Upload your audio or video file (up to 2GB). Required when Input Method is 'file_upload'.
youtubeUrl
stringOptional
YouTube video URL (e.g. https://youtube.com/watch?v=...). Required when Input Method is 'youtube'.
twitterUrl
stringOptional
Twitter or X post URL with video. Required when Input Method is 'twitter'.
gdriveUrl
stringOptional
Google Drive shareable link to audio/video file. Required when Input Method is 'gdrive'.
s3Url
stringOptional
AWS S3 URL or presigned URL to file. Required when Input Method is 's3'.
language
EnumOptional
Language of the audio (leave blank for auto-detect)
"en": string"es": string"fr": string"de": string"it": string"pt": string"ru": string"ja": string"ko": string"zh": string"ar": string"hi": string"nl": string"sv": string"no": string"da": string"fi": string"pl": string"cs": string"hu": string"ro": string"bg": string"hr": string"sk": string"sl": string"et": string"lv": string"lt": string
Default value of this property is ""
timestamps
EnumOptional
Include timestamps in the transcription
"none": string"segment": string"word": string"both": string
Default value of this property is "segment"
speakerDiarization
booleanOptional
Identify and separate different speakers in the audio
Default value of this property is false
minSpeakers
integerOptional
Minimum number of speakers expected (only used when Speaker Diarization is enabled)
Default value of this property is 1
maxSpeakers
integerOptional
Maximum number of speakers expected (only used when Speaker Diarization is enabled)
Default value of this property is 5
responseFormat
EnumOptional
Output format for the transcription
"json": string"text": string"srt": string"vtt": string
Default value of this property is "json"