Speech-to-Text Cost Calculator

Calculate the API cost of transcribing audio using a speech-to-text model.

About Speech-to-Text Cost Calculator

Speech-to-text providers bill per minute of audio processed. This calculator multiplies your total audio duration by the selected provider's per-minute rate to estimate transcription cost. Rates vary by provider and by features enabled (e.g. speaker diarization, custom vocabulary), so treat these as baseline estimates.

Formula

total_cost = audio_minutes × rate_per_minute

audio_minutes: Total audio duration in minutes
rate_per_minute: Provider cost per minute of audio

Worked example

With the default values below, Speech-to-Text Cost Calculator returns Total Cost of $0.3600. Change any input above and every figure here is recalculated in your browser.

Inputs used

Audio Durationaccepts 0–1,000,000 minutes: 60 minutes
Providerone of OpenAI Whisper API, AssemblyAI, Google Speech-to-Text, Azure Speech Services: OpenAI Whisper API

Results

Total Cost: $0.3600
Price per Minute: $0.0060

Step by step

1Total cost= $0.3600

Assumptions and limits

The result is derived only from the 2 inputs listed above. Anything not among them is not part of the calculation.
In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
Figures are rounded for display to 4 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Does audio quality affect the price?

No, most providers charge a flat per-minute rate regardless of audio quality, though very poor audio may increase error rates.

Is silence included in billed duration?

Typically yes — most providers bill for the full uploaded duration, including silence, unless you pre-trim the audio.

Do these rates include add-on features?

No, these are base transcription rates. Diarization, custom models, and real-time streaming often carry additional charges.