Speech to Text AI Marketplace

AI can transcribe speech into text, supporting multiple file types such as mp3, wav, and flac.

Header Parameters
X-API-Key string — REQUIRED Your API key

Request Body
files binary — REQUIRED Audio speech file
num_speakers number (optional) Number of speakers diarization in 1-4 speakers
word_timestamps string (optional) true or false // default 'false'
speaking_rate string (optional) true or false // default 'false'
decoder_type string (optional) Greedy, BeamSearch, or LMBeamSearch // default 'LMBeamSearch'
word_list string (optional) List of terminology ex. ['word', 'word', ...]

Responses
200 Return list of transcribed text that corresponds to speech detected in audio. Schema status string Status of transcription request data object Result data of transcription results object[] filename string Name of audio file duration string Total time(sec) of audio file predictions object[] List of outputs corresponds to speech detected in audio file transcript string Transcribed text start string Start time(sec) of transcribed text end string End time(sec) of transcribed text speaker_id number Speaker ID // optional speaking_rate string Speaking rate of each transcription // optional word_timestamps object[] List of time offsets of each word // optional word string Transcribed word // optional start_time string Start time(sec) offset of word // optional end_time string End time(sec) offset of word // optional
204 No content | No result of transcription
400 No audio file | Not found audio file or Bad requests | Server cannot or will not process the request
401 Unauthorized | Incorrect X-API-Key or X-API-Key not have access to this model
415 Can't decode [filename] | Unsupported file format