whisper api · drop-in · flat monthly

$10/month for 50 Whisper hours.

Same Whisper weights, same OpenAI-compatible API — change the base_url and nothing else. $0.20/hr if you use the whole allowance, $0.25/hr after it.

Provider$ / hr
AssemblyAI
Universal-2
$0.15
pay as you go
Google Cloud Speech
Dynamic batch (Standard)
$0.18
pay as you go
OpenAI
gpt-4o-mini-transcribe
$0.18
pay as you go
SpeakEasyincludes TTS
Pro plan
$0.20
$10/mo ÷ 50 hrs
AssemblyAI
Universal-3.5 Pro
$0.21
pay as you go
Deepgram
Nova-3 (pre-recorded)
$0.26
pay as you go
OpenAI
whisper-1 / gpt-4o-transcribe
$0.36
pay as you go
Google Cloud Speech
Standard recognition (v2)
$0.96
pay as you go

$0.20/hr is a plan rate, not a meter.

SpeakEasy is $10/month with 50 hours included, then $0.25 per additional hour. $0.20/hr is what you pay if you use all 50 hours; send only 10 hours and the same $10 works out to $1.00/hr. Every other provider here is true pay-as-you-go with no monthly minimum, so for transcription alone several of them cost less than this plan — do the arithmetic for your own volume before switching.

The 50 hours are a single shared allowance: transcription and text-to-speech both draw on it, so spending all of it on speech is ~3.3M characters — on the same OpenAI-compatible API, at no extra charge. None of the providers above bundle TTS with transcription at all.

Competitor prices read off each provider's own public pricing page on 2026-08-06; every provider name links to the page we read. Cheapest current pay-as-you-go rate shown for each, alongside their flagship model where it costs more.

// try it on a real file

Drop something below — meeting recording, voice memo, podcast clip. See the transcript and the actual API cost on the same screen.

One-line swap from OpenAI

cURL:

curl
curl https://www.tryspeakeasy.io/api/v1/audio/transcriptions \
  -H "Authorization: Bearer sk-se-YOUR_KEY_HERE" \
  -F file=@audio.mp3 \
  -F model=whisper-1

Node:

transcribe.ts
import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({
  apiKey: "sk-se-YOUR_KEY_HERE",
  baseURL: "https://www.tryspeakeasy.io/api/v1",
});

const transcript = await client.audio.transcriptions.create({
  file: fs.createReadStream("audio.mp3"),
  model: "whisper-1",
});

console.log(transcript.text);

Python user? Same thing in Python →

// the actual math

10,000 hours a month at OpenAI's whisper-1 = $3,600.00.
10,000 hours on this plan = $2,497.50.
10,000 hours at AssemblyAI Universal-2 = $1,500.00.

So: $1,102.50 a month back against the obvious route, and still $997.50more than the cheapest non-Whisper model on the table. If price per hour is your only constraint, go there. If you want Whisper's output through an API your code already speaks, this is the trade.

Get an API key →

FAQ

Is this actually a drop-in OpenAI Whisper replacement?+

Yes. Same endpoint shape (/audio/transcriptions), same request fields, same response JSON. If you point the OpenAI SDK at https://www.tryspeakeasy.io/api/v1 your existing code keeps working — no rewrite, no new SDK.

Is it actually cheaper than OpenAI?+

Against OpenAI's headline Whisper rate, once you're using the plan. $10 a month covers 50 hours — $0.20/hr if you fill the allowance, $0.25/hr after it — versus $0.36/hr metered at OpenAI ($0.006/min list). The crossover is about 28 hours a month; below that the flat fee costs you more, and at 10 hours it works out to $1.00/hr. It is not the cheapest transcription on the market either: AssemblyAI Universal-2 at $0.15/hr and OpenAI gpt-4o-mini-transcribe at $0.18/hr both beat this plan at every volume, on models that aren't Whisper. What you get here is Whisper's own output, an OpenAI-shaped API and one predictable bill.

Why is it cheaper than OpenAI's Whisper rate at all?+

Same Whisper model family, leaner deployment. OpenAI's list price bakes in a heavy margin and brand premium on top of the inference cost. We run the same checkpoint on commodity GPUs with aggressive batching and still hold a sustainable margin at a lower price. There's no quality trade-off because there's no model substitution — you're getting the same weights, just billed differently.

What about Deepgram or AssemblyAI?+

Priced closer than you'd expect. As of 2026-08-06 it's AssemblyAI Universal-2 at $0.15/hr and Deepgram Nova-3 (pre-recorded) at $0.26/hr, both pay-as-you-go with no monthly minimum. AssemblyAI undercuts this plan at every volume; Deepgram costs more than it once you're past roughly 39 hours a month. If you need speaker diarization or real-time streaming, Deepgram is the better tool. What you get here instead is Whisper itself behind an OpenAI-shaped endpoint, and text-to-speech drawing on the same allowance.

Are there rate limits I should worry about?+

The free playground above is rate-limited (5 transcriptions/day/IP) to stop abuse. The paid API has generous per-account limits — multi-thousand RPM on the entry plan. If you hit them, we lift them on request.

What languages does it handle?+

Whisper supports 99 languages out of the box. Our deployment passes that through unchanged — set language='auto' to detect, or hint a specific language code (e.g. 'en', 'de', 'es') to skip detection and shave a few hundred ms.

What's the catch?+

It's a monthly plan, not a meter, so light months cost more per hour than the table suggests — $0.20/hr assumes you use the whole allowance. We don't do streaming yet (working on it), we don't do speaker diarization (also coming), and TTS lives on a separate /audio/speech endpoint. For batch transcription of recorded audio at steady volume — meetings, podcasts, voice notes — the trade is a predictable bill and a one-line migration.