Implement Audio‑Input Features - Developer Guide

For developers requiring audio support, Infercom provides OpenAI’s Whisper large-v3 model, which enables real-time transcriptions and translations.

Whisper-Large-v3

• Model: Whisper-Large-v3
• Description: State-of-the-art automatic speech recognition (ASR) and translation model. Developed by OpenAI and trained on 5M+ hours of labeled audio. Excels in multilingual and zero-shot speech tasks across diverse domains.
• Model ID: Whisper-Large-v3
• Supported languages: Multilingual

Core capabilities

• Transcribes and translates extended audio inputs (up to 25 MB).
• Demonstrates high accuracy in speech recognition and translation tasks.
• Provides OpenAI-compatible endpoints for transcriptions and translations.

Request parameters

Parameter	Type	Description	Default	Endpoints
model	String	The ID of the model to use.	Required	transcriptions, translations
file	File	Audio file in FLAC, MP3, MP4, MPEG, MPGA, M4A, Ogg, WAV, or WebM format. File size limit: 25MB.	Required	transcriptions, translations
prompt	String	Prompt to influence transcription style or vocabulary. Example: “Please transcribe carefully, including pauses and hesitations.”	Optional	transcriptions, translations
response_format	String	Output format: json, text, verbose_json, srt or vtt. See Response formats below.	json	transcriptions, translations
timestamp_granularities[]	Array	Timestamp detail. Only segment is supported. Use it with verbose_json. word returns HTTP 400.	Optional	transcriptions
language	String	The language of the input audio. Using ISO-639-1 format (e.g., en) improves accuracy and latency.	Optional	transcriptions, translations
stream	Boolean	Enables streaming responses.	false	transcriptions, translations
stream_options	Object	Not supported. The endpoint rejects this parameter with HTTP 400 unknown_parameter.	-	Not accepted

Response formats

response_format accepts five values.

Value	What you get
json	A JSON object with text and a usage object: {"text": "...", "usage": {"type": "duration", "seconds": 5.58}}
text	The bare transcript string
verbose_json	A JSON object with duration, language, task, text and segments. Each segment has an id, a start and an end time in seconds, and its text. There is no usage object
srt	SRT subtitles with numbered cues and timestamps
vtt	WebVTT subtitles. The body starts with WEBVTT

To get segment timestamps in JSON, send response_format=verbose_json with timestamp_granularities[]=segment. Word-level timestamps are not supported: timestamp_granularities[]=word returns HTTP 400.

Usage data

With response_format=json, transcriptions and translations return a usage object. usage.seconds is the duration of the processed audio, in seconds. The other formats return no usage object.

Note

stream_options: {"include_usage": true} is not supported. The endpoint rejects the parameter with HTTP 400.

Example usage

Python (SambaNova SDK)

from sambanova import SambaNova
import base64

client = SambaNova(
    base_url="https://api.infercom.ai/v1",
    api_key="your-infercom-api-key",
)

audio_path="audio_path"
with open(audio_path, "rb") as audio_file:
   bin_audio = audio_file.read()

response = client.audio.transcriptions.create(
    model="Whisper-Large-v3",
    file=(audio_path,bin_audio),
)
print(str(response))

Python (OpenAI)

from openai import OpenAI
import base64

client = OpenAI(
    base_url="https://api.infercom.ai/v1",
    api_key="your-infercom-api-key",
)

audio_path="audio_path"
with open(audio_path, "rb") as audio_file:
   bin_audio = audio_file.read()

response = client.audio.transcriptions.create(
    model="Whisper-Large-v3",
    file=(audio_path,bin_audio),
)
print(str(response))

Javascript (SambaNova SDK)

import SambaNova from "sambanova";

const client = new SambaNova({
  baseURL: 'https://api.infercom.ai/v1',
  apiKey: 'your-infercom-api-key'
});

async function run() {
  const audioPath = 'audio_path';
  const binAudio = fs.createReadStream(audioPath);

  const response = await client.audio.transcriptions.create({
    model: 'Whisper-Large-v3',
    file: binAudio,
  });

  console.log('Full Response:');
  console.dir(response, { depth: null });
}

run().catch(console.error);