100% OpenAI SDK Compatible

Speech to Text APIWhisper API Alternative

Integrate highly accurate audio transcription into your app in seconds. Swap out your OpenAI base URL to get built-in speaker diarization at half the cost.

Buy Credits & Get KeyView Documentation
No Monthly Fees
Pay As You Go
python_sdk_example.py
from openai import OpenAI

# 1. Just change the base_url and api_key!
client = OpenAI(
  api_key="fat-xxxxxxxxx",
  base_url="https://api.freeaudiototext.com/v1"
)

# 2. Use the exact same code you already wrote
transcript = client.audio.transcriptions.create(
  model="whisper-1",
  file=open("meeting.mp3", "rb"),
  response_format="diarized_json" # We support speakers!
)

print(transcript.segments[0].speaker) # Output: "SPK_1"

Why switch from OpenAI Whisper?

Native Speaker Diarization

Unlike OpenAI's API which returns a giant wall of text, our advanced models automatically separate speakers (e.g., SPK_1, SPK_2) with precise word-level timestamps for English and Chinese.

Zero Code Changes

Fully compatible with the official `openai-python` and Node.js SDKs. Just point the `base_url` to our servers. No new libraries to learn, no architectural rewrites required.

50% Lower Costs

OpenAI charges $0.006 per minute. Our API starts at just $0.003 per minute. Save thousands of dollars scaling your transcription startup without sacrificing accuracy.

API Documentation & Output Example

Pass response_format="diarized_json" in your request to receive speaker labels alongside your transcription segments. We strictly follow the OpenAI schema.

JSON Response (Diarized)
{
  "task": "transcribe",
  "duration": 27.4,
  "language": "english",
  "text": "Thanks for calling support. Hi, I'm trying to enable diarization...",
  "segments": [
    {
      "id": "seg_001",
      "start": 0.0,
      "end": 4.7,
      "text": "Thanks for calling support.",
      "speaker": "SPK_1"
    },
    {
      "id": "seg_002",
      "start": 4.7,
      "end": 11.8,
      "text": "Hi, I'm trying to enable diarization.",
      "speaker": "SPK_2"
    }
  ],
  "usage": {
    "type": "duration",
    "seconds": 27
  }
}

Pay As You Go Pricing

Buy prepaid credits. No subscriptions. No expiring tokens.

Hobby

Perfect for testing & side projects

$4.90
  • 20 Hours of Audio
  • $0.245 / hour
Most Popular

Pro

For indie hackers & active apps

$19.00
  • 150 Hours of Audio
  • $0.126 / hour (65% off OpenAI)

Agency

High volume transcription

$49.00
  • 500 Hours of Audio
  • $0.098 / hour
Payment securely processed by Waffo. Your API key will be delivered via email instantly.

Frequently Asked Questions

How do I receive my API key after payment?
Immediately after a successful checkout, our system will securely generate a unique API Key and email it directly to the email address you provided during payment. No account registration is required!
Are my audio files stored on your servers?
No. We are a privacy-first API. Audio files are processed in memory and immediately discarded. We do not store your audio data, nor do we use it to train any models.
Does speaker diarization work for all languages?
Highly accurate word-level speaker diarization (separating overlapping voices) is fully supported for English and Chinese. For other 30+ languages, we use VAD (Voice Activity Detection) fallback to split speakers based on natural pauses.
How can I check my remaining API credit balance?

You can perform a simple GET request to our /v1/balance endpoint using your API Key as the Bearer Token:

curl https://api.freeaudiototext.com/v1/balance \ -H "Authorization: Bearer fat-xxxxxxxxx"

It will instantly return your remaining balance in both seconds and minutes.