service is live

Audio transcription to text
via API

Turn calls, voice messages and interviews into text in 99 languages. Connecting takes one line of code — only the base URL and the key change.

10 minutes free — credited to your balance once you confirm your email

After that — up to 0.006 USD per minute of audio, pay as you go

Get an API key — 10 min free Client area

Why teams choose voicescribe

99 languages, no setup

The language is detected automatically: English, Spanish, Polish, Russian and dozens more in a single stream.

Results in seconds

A minute of audio is transcribed in a couple of seconds and returned in the same request — no queues, no polling.

Data does not pile up

Recordings and transcripts live no longer than 24 hours — just long enough to verify quality — then they are deleted.

Keep your code

Only the base URL and the key change — calls, parameters and response parsing stay as they are. Response and error formats are identical.

Plans and pricing

What we sell: audio-to-text transcription over an API. New clients start with 10 free minutes. Only successfully processed requests are billed — failed ones consume no minutes. Billing currency — USD.

Standard

0.006 USD per minute of audio
Up to 2 req/s

You pay by topping up the balance right from the client area: a crypto transfer is credited automatically, usually within minutes. Minutes are deducted as they are processed; when the balance hits zero requests are rejected, and a top-up lifts the block immediately. The remaining balance, request history and the invoice for the period are in the same place. Need a proper invoice or running large volumes — write to support@voicesscribe.com and we will agree on the rate.

Connect in a minute

Already transcribing somewhere else? Replace two lines.

from openai import OpenAI

client = OpenAI(base_url="https://voicesscribe.com/v1", api_key="your key")
r = client.audio.transcriptions.create(model="whisper-1", file=open("call.ogg", "rb"))
print(r.text)
1
Get a key

Sign-up takes a minute; the key is issued instantly along with client area access.

2
Change the base URL

The official openai-sdk works as is: point it at our endpoint with your key — the rest of your code stays untouched.

3
Track usage

Minutes, transcript history and the invoice for the period are in your client area, live.

Speech recognition API features

A single endpoint POST /v1/audio/transcriptions — everything else is a parameter.

Audio formats

ogg · opus · mp3 · wav · m4a · webm — up to 25 MB

Response formats

json · text · verbose_json · srt · vtt

Term hints

The prompt parameter improves accuracy for names, brands and codes.

Subtitles and timings

Ready-made srt and vtt, or timed segments in verbose_json.

Guides and examples

Step-by-step instructions for the usual tasks — with code and error handling.

All articles →

Frequently asked questions

Do I have to rewrite my code?

No. Calls, parameters and response formats match the standard transcription API — only the base URL and the key change. Recognition runs on our own hardware.

Which languages are supported?

99 languages including English, Spanish, German, Polish and Russian. The language is detected automatically, specifying it is optional.

How fast is transcription?

One minute of audio takes a couple of seconds. The text comes back in the same request — no status polling required.

What happens to uploaded recordings?

Recordings and transcripts are kept for no longer than 24 hours so you can verify quality, then deleted automatically.

Which audio formats are accepted?

ogg, opus, mp3, wav, m4a, webm and other common formats up to 25 MB. Responses are available as json, text, verbose_json, srt and vtt.

How much does it cost?

Billing is per minute of audio: up to 0.006 USD per minute, with volume pricing on request. Only successfully processed requests are billed — failed requests do not consume minutes.