---
title: "Speech-to-text API pricing compared per minute (2026)"
description: "Per-minute and per-1,000-hour prices for OpenAI, Google, AWS, Deepgram, AssemblyAI, Speechmatics, Groq and BroadNet Transcribe from official pages, plus add-ons."
url: https://broadrouter.com/blog/speech-to-text-api-pricing-compared/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Speech-to-text API pricing compared: price per minute in 2026

By the BroadNet Inference team · 7 min read · Published 2026-11-14 · Updated 2026-11-15

Batch speech-to-text APIs cost roughly USD 0.0007 to 0.016 per audio minute at list price in November 2026. Deepgram Nova-3 charges USD 0.0043, OpenAI's current gpt-transcribe USD 0.0045, AWS Transcribe USD 0.006 and Google V2 standard USD 0.016. BroadNet Transcribe costs $0.002 a minute in 14 languages, and BroadNet Transcribe Arabic $0.0042.

## Key takeaways

-   List prices for batch transcription span more than 20x, from about USD 0.04 to USD 0.96 per audio hour.
-   Add-ons change the bill: diarization, PII redaction and streaming can each cost extra.
-   Compare per 1,000 hours, the unit most volume is measured in, and include billing minimums.
-   BroadNet Transcribe costs $0.12 per audio hour; BroadNet Transcribe Arabic costs $0.25, or $252.00 per 1,000 hours.
-   Price is only half the decision. Measure word error rate on your own audio before you switch.

**On this page**

1.  How much do speech-to-text APIs cost per minute and per 1,000 hours?
2.  What does the base price leave out?
3.  What do 10,000 voice notes a month cost to transcribe?
4.  What matters besides price?
5.  Where BroadNet Transcribe fits

Speech-to-text pricing looks simple: a price per minute of audio. In practice, providers quote per minute, per hour or per second, split batch from streaming, and sell diarization and redaction as add-ons. This page puts the main APIs on one scale, using prices we fetched from each official page on **14 and 15 November 2026** (each source below gives its date).

All prices are list, pay-as-you-go, in US dollars, for batch (pre-recorded) audio unless noted. Volume discounts and contracts are not included.

## How much do speech-to-text APIs cost per minute and per 1,000 hours?

| Provider and model | Per minute | Per hour | Per 1,000 hours |
| --- | --- | --- | --- |
| Groq, Whisper Large v3 Turbo | about USD 0.00067 | USD 0.04 | USD 40 |
| DeepSeek ASR, limited-time price (50% off list) | about USD 0.00097 | USD 0.058 | USD 58 |
| Soniox, async (billed per token; “about” per hour) | about USD 0.00167 | about USD 0.10 | about USD 100 |
| Groq, Whisper Large v3 | about USD 0.00185 | USD 0.111 | USD 111 |
| DeepSeek ASR, list price | about USD 0.00193 | USD 0.116 | USD 116 |
| [BroadNet Transcribe](https://broadrouter.com/models/cohere-transcribe/) (14 languages) | $0.002 | $0.12 | $120.00 |
| AssemblyAI, Universal-2 | USD 0.0025 | USD 0.15 | USD 150 |
| OpenAI, gpt-4o-mini-transcribe (deprecated, shuts down 2027-02-26) | USD 0.003 | USD 0.18 | USD 180 |
| Google, V2 dynamic batch | USD 0.003 | USD 0.18 | USD 180 |
| AssemblyAI, Universal-3.5 Pro | USD 0.0035 | USD 0.21 | USD 210 |
| Speechmatics, Melia 1 multilingual (56 languages) | USD 0.004 | USD 0.24 | USD 240 |
| [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/) | $0.0042 | $0.25 | $252.00 |
| Deepgram, Nova-3 monolingual | USD 0.0043 | USD 0.258 | USD 258 |
| OpenAI, gpt-transcribe | USD 0.0045 | USD 0.27 | USD 270 |
| Deepgram, Nova-3 multilingual | USD 0.0052 | USD 0.312 | USD 312 |
| OpenAI, whisper-1 / gpt-4o-transcribe (deprecated, shut down 2027-02-26) | USD 0.006 | USD 0.36 | USD 360 |
| AWS Transcribe, batch (US East) | USD 0.006 | USD 0.36 | USD 360 |
| Speechmatics, Standard | USD 0.0075 | USD 0.45 | USD 450 |
| Speechmatics, Enhanced | USD 0.0125 | USD 0.75 | USD 750 |
| Google, V2 standard (first 500,000 min) | USD 0.016 | USD 0.96 | USD 960 |

Per-hour and per-1,000-hour figures are our arithmetic from the published unit price (per minute x 60, then x 1,000). Groq, DeepSeek, AssemblyAI and Speechmatics publish per-hour prices; we divided by 60 for the per-minute column. DeepSeek’s [pricing page](https://api-docs.deepseek.com/quick_start/pricing) lists its speech-to-text API at USD 0.116 an hour with a limited-time 50% discount and gives no end date, so budget on the list price. Speechmatics rates are its list pre-recorded prices; its pricing page can also show them with a 33% model-training discount and up to 25% volume discount applied, which brings Melia 1 down to about USD 0.12 an hour. The 33% discount is opt-in, and by opting in you let Speechmatics use your audio and transcripts to improve its models (its pricing FAQ, checked 2026-11-15).

Soniox, DeepSeek ASR and Groq’s Whisper endpoints all cost less per hour than both BroadNet models. Soniox’s [pricing page](https://soniox.com/pricing), checked 2026-11-14, bills per token (USD 1.50 per 1M input audio tokens and USD 3.50 per 1M output text tokens for async) and says this is “about” USD 0.10 an hour for file uploads and USD 0.12 an hour for real-time streaming. Its [language list](https://docs.soniox.com/stt/concepts/supported-languages) includes Arabic among more than 60 languages. It uses its own job-based API rather than the OpenAI `/v1/audio/transcriptions` shape, so switching to it means new client code.

One change to plan for: OpenAI’s [deprecations page](https://developers.openai.com/api/docs/deprecations), checked 2026-11-15, lists `whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` and `gpt-4o-transcribe-diarize` as deprecated (notice given August 26, 2026), shutting down on February 26, 2027, with `gpt-transcribe` or `gpt-live-transcribe` as the replacement. Its pricing page marks the same four models deprecated. If you price an OpenAI pipeline today, price it on `gpt-transcribe` at USD 0.0045 a minute. That is more per hour than both BroadNet models, but OpenAI also sells live transcription (`gpt-live-transcribe`, USD 0.017 a minute), which BroadNet does not. This page compares prices only; if you are moving off `whisper-1`, the [Whisper API alternative guide](https://broadrouter.com/blog/whisper-api-alternative/) covers how to test a replacement on your own audio and what breaks in the switch. To run your own volumes against these rates, use the [speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/).

For the full picture, our open [speech-to-text API price index](https://broadrouter.com/data/speech-to-text-api-prices/) lists batch and streaming prices, billing increments and Arabic support for more than 20 products, each checked against the provider’s own pricing page (CSV and JSON).

## What does the base price leave out?

The per-minute number is rarely the whole bill. Check these before you compare:

| Item | What the pages say |
| --- | --- |
| Speaker diarization | Deepgram: included for pre-recorded, USD 0.0020/min extra for streaming. AWS: included in the standard price. AssemblyAI: +USD 0.02/hr. OpenAI: separate `gpt-4o-transcribe-diarize` model at USD 0.006/min, deprecated and shutting down 2027-02-26. |
| PII redaction | Deepgram: USD 0.0020/min. AWS: USD 0.0024/min (tier 1). AssemblyAI: text redaction +USD 0.08/hr on Universal-2 and +USD 0.12/hr on Universal-3.5 Pro; audio redaction +USD 0.05/hr. |
| Streaming | AWS: USD 0.01/min vs USD 0.006 batch. Deepgram Nova-3 monolingual: USD 0.0048 streaming (a promotional price valid until 2027-02-13) vs USD 0.0043 pre-recorded. Speechmatics Melia 1: USD 0.40/hr real-time vs USD 0.24/hr pre-recorded. |
| Billing minimum | Groq bills at least 10 seconds per request. AWS bills per second with no minimum. Google rounds each request up to the next second. |
| Volume tiers | Google V2 standard drops to USD 0.01/min after 500,000 minutes a month, and lower above 1 million. AWS standard batch and streaming are now flat rates; its volume tiers apply to add-ons such as redaction. |

For a call centre that needs diarization and redaction, Deepgram Nova-3 pre-recorded becomes USD 0.0063 per minute with redaction, and AWS becomes USD 0.0084. A cheap base price with expensive add-ons can lose to a higher base price with them included.

## What do 10,000 voice notes a month cost to transcribe?

Say a support inbox receives 10,000 WhatsApp voice notes a month, 30 seconds each. That is 5,000 minutes.

-   At USD 0.006 a minute (AWS batch, or OpenAI’s deprecated whisper-1): USD 30.
-   At USD 0.0045 (OpenAI gpt-transcribe): USD 22.50.
-   At USD 0.0043 (Deepgram Nova-3): USD 21.50.
-   On BroadNet Transcribe Arabic: $21.00.

Billing minimums matter here. Groq’s 10-second minimum does not change the bill for these 30-second notes, but it bills a two-second “ok” note as 10 seconds. With a 15-second minimum, that two-second note costs the same as a 15-second one. For the full voice-note workflow, see [voice notes to text for business](https://broadrouter.com/blog/voice-notes-to-text-for-business/).

## What matters besides price?

A cheaper model that gets 1 word in 5 wrong costs more in human correction than it saves. Before switching, measure [word error rate](https://broadrouter.com/glossary/word-error-rate/) on 30 to 50 of your own recordings per language. Our [Whisper alternative guide](https://broadrouter.com/blog/whisper-api-alternative/) shows how to run that test in an afternoon, and the [Arabic speech-to-text buyer’s guide](https://broadrouter.com/blog/arabic-speech-to-text-api-buyers-guide/) covers dialect-by-dialect scoring.

Other non-price questions:

-   **Languages.** BroadNet Transcribe covers 14 languages ([full list](https://broadrouter.com/blog/multilingual-speech-to-text-api/)); OpenAI says Whisper (the deprecated `whisper-1`) supports 98 with varying accuracy.
-   **File limits.** OpenAI caps uploads at 25 MB and BroadNet at 25 MiB, so split long calls.
-   **Retention.** Audio is often more sensitive than text. Ask whether audio and transcripts are stored; see [LLM API data retention compared](https://broadrouter.com/blog/llm-api-data-retention-compared/).

## Where BroadNet Transcribe fits

BroadNet Transcribe costs $0.002 a minute ($0.12 an hour) across 14 languages: English, Spanish, French, German, Italian, Portuguese, Greek, Dutch, Polish, Chinese, Japanese, Korean, Vietnamese and Arabic. BroadNet Transcribe Arabic costs $0.0042 a minute and is built for Arabic dialects; BroadNet reports it #2 of 37 (its September 2026 figure; the live board listed it #4 of 39 on 15 November 2026) on the Open Universal Arabic ASR Leaderboard. Both use the OpenAI-compatible `/v1/audio/transcriptions` endpoint, accept WAV or MP3 up to 25 MiB, and keep no audio or transcripts ([zero data retention](https://broadrouter.com/zero-data-retention/)). The $5 starting credit covers about 1,190 minutes of Arabic audio; [create a key](https://inference.broadnet.ai/?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-speech-to-text-api-pricing-compared&utm_content=body) to test your own files.

Where it does not fit: BroadNet does not list streaming transcription, built-in diarization or redaction add-ons. If you need live captions or speaker labels from the API itself, Deepgram, AssemblyAI and AWS offer both. OpenAI offers live transcription, but its only speaker-labelling model is deprecated. Compare the two BroadNet models side by side on the [comparison page](https://broadrouter.com/compare/cohere-transcribe-vs-cohere-transcribe-arabic/), or see all prices on [pricing](https://broadrouter.com/pricing/).

Free tools for this

-   [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/) Price a workload on every model at once, with cache hits, reasoning and a flat-plan check.
-   [LLM token counter](https://broadrouter.com/tools/token-counter/) Exact token counts with each model's real tokenizer, with a token view and cost.
-   [Context window calculator](https://broadrouter.com/tools/context-window-calculator/) Will it fit? Window used per model, room left for output, cost to send.

[All free tools](https://broadrouter.com/tools/)

## Terms in this article

[Speech-to-text](https://broadrouter.com/glossary/speech-to-text/)

Speech-to-text, also called automatic speech recognition (ASR), is technology that converts spoken audio into written text. A speech-to-text API accepts an audio file or stream and returns a transcript, usually priced per minute of audio. Accuracy is measured with word error rate and varies with accent, dialect and recording quality.

[Streaming](https://broadrouter.com/glossary/streaming/)

Streaming is a way of returning a language model response in small chunks while it is still being generated, instead of as one reply at the end. OpenAI-compatible APIs stream over server-sent events when the request sets stream to true.

[Token](https://broadrouter.com/glossary/token/)

A token is the unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence produced by the model's tokenizer. LLM APIs count, limit and usually bill usage in tokens.

[Dialectal Arabic](https://broadrouter.com/glossary/dialectal-arabic/)

Dialectal Arabic is the everyday spoken Arabic of a region or city, such as Egyptian, Gulf, Levantine or Maghrebi Arabic. Dialects differ from Modern Standard Arabic in sounds, words and grammar, have no standard spelling, and are increasingly written online, which makes them harder for language models.

[PII (personally identifiable information)](https://broadrouter.com/glossary/pii/)

PII (personally identifiable information) is information that can be used to distinguish or trace a person's identity, such as a name, ID number or biometric record, plus other information linked or linkable to that person. The GDPR's broader term is personal data. In LLM work, PII redaction removes it from prompts before they leave your systems.

[Speaker diarization](https://broadrouter.com/glossary/diarization/)

Speaker diarization is the task of dividing an audio recording into segments by speaker, answering "who spoke when". It labels each stretch of speech with an anonymous speaker ID such as SPEAKER\_00, and is usually combined with a transcript to show which person said each line.

[Pay-as-you-go](https://broadrouter.com/glossary/pay-as-you-go/)

Pay-as-you-go is a pricing model in which you pay only for what you use, metered per unit such as tokens, requests or audio minutes, with no subscription or minimum commitment. Most LLM APIs bill this way, from a prepaid balance or a periodic invoice.

[Tool calling](https://broadrouter.com/glossary/tool-calling/)

Tool calling, also called function calling, is an LLM API feature in which the model returns a structured request to run a function the developer has defined, with JSON arguments. The application runs the function and sends the result back; the model never runs code itself.

## Questions

### What is the cheapest speech-to-text API?

In November 2026, Groq's Whisper Large v3 Turbo at USD 0.04 per hour was the lowest in our table. DeepSeek ASR came next at USD 0.058 an hour, but only while its limited-time 50% discount lasts (no end date given). Then came Soniox at about USD 0.10 an hour (async), Groq Whisper Large v3 at USD 0.111, DeepSeek ASR at its USD 0.116 list price and BroadNet Transcribe at $0.12 an hour. Accuracy on your audio decides whether cheap is good enough.

### How much does the OpenAI Whisper API cost per minute?

OpenAI lists whisper-1 at USD 0.006 per minute, the same as gpt-4o-transcribe; gpt-4o-mini-transcribe is USD 0.003. All three are marked deprecated on its pricing page, and its deprecations page says they shut down on February 26, 2027. Its recommended replacement, gpt-transcribe, costs USD 0.0045 a minute (USD 0.27 an hour). Checked 2026-11-15.

### How much does it cost to transcribe 1,000 hours of audio?

Multiply the per-minute price by 60,000. At USD 0.006 a minute that is USD 360. With BroadNet Transcribe Arabic it is $252.00.

### Is speaker diarization included in the price?

It varies. Deepgram includes it for pre-recorded audio and AWS in its standard price, AssemblyAI charges extra per hour, and OpenAI's only diarization model, gpt-4o-transcribe-diarize, is deprecated and shuts down on February 26, 2027. Check before you compare base prices.

### Is streaming transcription more expensive than batch?

Usually. AWS lists USD 0.006 a minute for batch and USD 0.01 for streaming, and Deepgram charges more for streaming Nova-3 than for pre-recorded.

## Keep reading

-   [Whisper API alternative: when to switch, and how to test one](https://broadrouter.com/blog/whisper-api-alternative/)
-   [Arabic speech-to-text API: how to choose one in 2026](https://broadrouter.com/blog/arabic-speech-to-text-api-buyers-guide/)
-   [How to transcribe call center recordings: an Arabic-ready pipeline](https://broadrouter.com/blog/transcribe-call-center-recordings/)
-   [Voice notes to text for business: WhatsApp and Telegram to tickets](https://broadrouter.com/blog/voice-notes-to-text-for-business/)
-   [Artificial Analysis alternatives: where to compare LLMs in 2026](https://broadrouter.com/blog/artificial-analysis-alternatives/)
-   [Live, on request, research: read a model catalogue clearly](https://broadrouter.com/blog/understand-model-status/)
-   [Guide: Arabic speech-to-text API, step by step](https://broadrouter.com/guides/arabic-speech-to-text-api/)
-   [Guide: Transcribe WhatsApp voice notes to text with an API](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-speech-to-text-api-pricing-compared&utm_content=page-cta) ·

**Sources**

-   [OpenAI API pricing, transcription (fetched 2026-11-15)](https://developers.openai.com/api/docs/pricing)
-   [OpenAI deprecations, speech-to-text models (fetched 2026-11-15)](https://developers.openai.com/api/docs/deprecations)
-   [Google Cloud Speech-to-Text pricing (fetched 2026-11-14)](https://cloud.google.com/speech-to-text/pricing)
-   [Amazon Transcribe pricing (fetched 2026-11-14)](https://aws.amazon.com/transcribe/pricing/)
-   [Deepgram pricing (fetched 2026-11-14)](https://deepgram.com/pricing)
-   [AssemblyAI pricing (fetched 2026-11-14)](https://www.assemblyai.com/pricing)
-   [Speechmatics pricing, with its model-training discount FAQ (fetched 2026-11-14; FAQ checked 2026-11-15)](https://www.speechmatics.com/pricing)
-   [Soniox pricing (fetched 2026-11-14)](https://soniox.com/pricing)
-   [Soniox supported languages (fetched 2026-11-14)](https://docs.soniox.com/stt/concepts/supported-languages)
-   [DeepSeek API pricing, speech to text (fetched 2026-11-14)](https://api-docs.deepseek.com/quick_start/pricing)
-   [Groq speech-to-text docs, Whisper prices (fetched 2026-11-14)](https://console.groq.com/docs/speech-to-text)
-   [BroadNet Inference machine-readable prices (pricing.json)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-speech-to-text-api-pricing-compared&utm_content=sources)
