Audio Transcription Cost Calculator

✓ Last verified: 2026-07-15· Source: official provider pricing page· Auto-monitored — report change →

Transcription is billed per minute of audio, and the cheapest provider can be five times less than the priciest. Enter your monthly audio to rank every speech-to-text API by what you'd actually pay.

Per-minute pricing, five-fold spread

Speech-to-text APIs bill by the minute of audio, not by file size or word count, which makes volume planning simple: estimate your hours, multiply by sixty, multiply by the per-minute rate. The catch is how wide the spread is. Deepgram and AssemblyAI's batch tiers transcribe a minute for well under half a cent, OpenAI's Whisper API sits around six tenths of a cent, and the hyperscaler services — Google, AWS Transcribe, Azure — typically charge two to four times more per minute. Over thousands of hours a month, that gap turns into thousands of dollars a year for identical output.

Batch vs real-time is the other big dial

The second cost lever is latency. Real-time streaming transcription — live captions, voice agents, call monitoring — holds an open connection and returns words as they're spoken, and providers charge a premium for it. Batch transcription of recorded files runs in the background and is markedly cheaper. If your product can wait a few minutes — meeting summaries, podcast transcripts, archived call analytics — use batch and pocket the difference. Only pay for real-time where the user is genuinely waiting on the words.

When to self-host Whisper

Open-source Whisper removes the per-minute fee but adds GPU, ops and idle cost. Below a few hundred hours a month the hosted API wins on both price and simplicity; above that, a well-utilised GPU running near the clock can beat it. Find your crossover on the self-hosted vs API calculator. If transcription feeds an LLM — summaries, Q&A over calls — add that token cost on the LLM token cost calculator, and total the whole pipeline on the AI app cost estimator.

Related tools & guides

AI app cost estimator · Self-hosted vs API calculator · AI voice agent cost calculator · Cheapest LLM API · All AI APIs

Frequently asked questions

How much does speech-to-text cost per minute?

In 2026, transcription APIs bill roughly $0.0037 to $0.024 per minute of audio. Deepgram and AssemblyAI's batch tiers sit at the cheap end (well under half a cent a minute), OpenAI Whisper is around $0.006, and the big-cloud services — Google, AWS, Azure — are typically more expensive per minute but bundle into existing cloud accounts. Real-time streaming usually costs more than batch transcription of recorded files.

Why is real-time transcription more expensive than batch?

Streaming speech-to-text holds a live connection and returns partial results with low latency, which is more compute-intensive than transcribing a finished file in the background. Most providers charge a premium for real-time over batch. If your use case can tolerate a few minutes of delay — meeting notes, podcast transcripts, call analytics — batch mode is noticeably cheaper for the same audio.

Is open-source Whisper cheaper than the API?

Running open-source Whisper on your own GPU removes the per-minute fee, but you pay for the GPU, ops and idle time. Below a few hundred hours a month the hosted API is almost always cheaper and far simpler; above that, self-hosting can win. The crossover depends on utilisation — a GPU transcribing 24/7 amortises well, one used a few hours a day does not.