Transcription

Converts audio to text in the specified language.

Endpoint

POST https://api.sambanova.ai/v1/audio/transcriptions

Request parameters

The following tables outline the parameters required to make a transcription request, parameter type, description, and default values.

Whisper Large v3

Parameter	Type	Description	Default
model	String	The ID of the model to use.	Required
prompt	String	Prompt provided to influence transcription style or vocabulary. Example: Please transcribe carefully, including pauses and hesitations. “	Optional
temperature	Number	Sampling temperature between 0 and 1. Higher values (e.g., 0.8) increase randomness, while lower values (e.g., 0.2) make output more focused.	0
file	File	Audio file in FLAC, MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. File size limit is 25MB.	Required
response_format	String	Output format: JSON or text.	json
language	String	The language of the input audio. Supplying the input language in ISO-639-1 (e.g. en) format will improve accuracy and latency.	Required

Qwen2-Audio-7B-Instruct

Parameter	Type	Description	Default
model	String	The ID of the model to use.	Required
messages	Message	A list of messages containing role (user/system/assistant), type (text/audio_content), and audio_content (base64 audio content).	Required
response_format	String	The output format is either json or text.	json
temperature	Number	Sampling temperature between 0 and 1. Higher values (e.g., 0.8) increase randomness, while lower values (e.g., 0.2) make output more focused.	0
max_tokens	Number	The maximum number of tokens to generate.	1000
file	File	Audio file in FLAC, MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. Each single file must not exceed 30 seconds in duration.	Required
language	String	The target language for transcription or translation.	Optional
stream	Boolean	Enables streaming responses.	false
stream_options	Object	Additional streaming configuration (e.g., {“include_usage”: true}).	Optional

Request format

CURL

This section provides examples of how to send a request using different methods.

curl --location 'https://api.sambanova.ai/v1/audio/transcriptions' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--form 'model="Qwen2-Audio-7B-Instruct"' \
--form 'language="spanish"' \
--form 'response_format="json"' \
--form 'temperature="0.01"' \
--form 'file=@"/path/to/audio/file.mp3"' \
--form 'stream="true"'

Python

helloWorld.py

import requests

def transcribe_audio(audio_file_path, api_key, language="english"):
  headers = {"Authorization": f"Bearer {api_key}"}

  files = {"file": open(audio_file_path, "rb")}

  data = {
      "model": "Qwen2-Audio-7B-Instruct",
      "language": language,
      "response_format": "json",
      "temperature": 0.01,
      "stream": true,  # Optional
  }

  response = requests.post(
      "https://api.sambanova.ai/v1/audio/transcriptions",
      headers=headers,
      files=files,
      data=data,
  )

  return response.json()

Response format

The API returns a translation of the input audio in the selected format.

JSON

{
    "text": "It's a sound effect of a bell chiming, specifically a church bell."
}

Text

It's a sound effect of a bell chiming, specifically a church bell.