Speech-to-text API
Google Cloud Speech-to-Text
Speech to text over gRPC and REST for recorded and live audio (V1 and V2 APIs), billed per minute of audio in one-second increments.
Plans
Values that apply to one plan. "Not stated" means the official pages do not say; it is not an estimate.
| Plan | Price | Included | Extra usage | Concurrency | Rate limit | Buy |
|---|---|---|---|---|---|---|
| V2 API Standard recognition (pay as you go)Pay as you go | Not recorded | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | ||
| V2 API Dynamic Batch (pay as you go)Pay as you go | Not recorded | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | ||
| V1 API (no data logging, pay as you go)Pay as you go | Not recorded |
Not recorded |
Pricing pageChoose the plan on the page | |||
| Streaming recognition (rate not separated)Pay as you goPrice not published · not in search | Not stated20 |
Not recorded | Not recorded |
Not recorded |
Not recorded |
Pricing pageChoose the plan on the page |
Applies to every plan
Recorded for the product or the provider; a plan-level value or a listed exception replaces it.
- Data storage or processing region (all products)
- Not stated1
Collection notes
Three priced plans of the pay-as-you-go prices of the pricing page and an unpriced streaming plan. V2 Standard recognition is priced per minute in four monthly volume steps; the plan records the first step ($0.016 a minute for the first 500,000 minutes a month, about 8,333 audio hours), so the cost of a month beyond that is an upper bound (the later steps are $0.01, $0.008 and $0.004). V2 Dynamic Batch is $0.003 a minute. The V1 API plan is the default without data logging: the first 60 minutes a month are free, then $0.024 a minute ($0.016 with data logging opted in, which is not the recorded price). The pricing page has no separate streaming row, so no plan states a streaming price. Authentication is by Google Cloud credentials (Application Default Credentials, gcloud, service accounts); no API key sentence and no Speech-to-Text MCP server page were found.
Sources and notes
Each number points to the provider's own sentence, as it appears on the page on the date shown.
The pages read for pricing and the V1 guides state no data storage or processing region choice for the plans recorded.
The pricing page prices recognition requests without a separate row for live audio, so the price for streaming is not stated.
The pricing page prices recognition requests without separating recorded from live audio.
Recognition (sku:3099-B70F-0949) Standard 0 minute to 500,000 minute $0.016 / 1 minute, per 1 month / account 500,000 minute to 1,000,000 minute $0.01 / 1 minute, per 1 month / account 1,000,000 minute to 2,000,000 minute $0.008 / 1 minute, per 1 month / account 2,000,000 minute and above $0.004 / 1 minute, per 1 month / account
How the value follows from the source: $0.016 per audio minute x 60 = $0.96 per audio hour, so $960 per 1,000 audio hours (the first monthly step).
How the value follows from the source: $0.016 per audio minute x 60 x 1,000.
The Speech-to-Text V2 API has an option to use dynamic batch.
Dynamic Batch is the lower-urgency recorded-audio option; no sentence on the pages read states whether it serves live audio.
Dynamic Batch Recognition (sku:7700-6778-EF8E) Standard¹ $0.003 / 1 minute, per 1 month
How the value follows from the source: $0.003 per audio minute x 60 = $0.18 per audio hour, so $180 per 1,000 audio hours.
How the value follows from the source: $0.003 per audio minute x 60 x 1,000.
The pricing page has no separate row for live audio, so whether this price covers streaming is not stated.
The pricing page does not separate recorded from live audio in this row.
Speech Recognition (without data logging) sku:60AE-2FE3-C3D8 Standard¹ 0 minute to 60 minute $0.00 (Free) / 1 minute, per 1 month / account 60 minute and above $0.024 / 1 minute, per 1 month / account
How the value follows from the source: $0.024 per audio minute x 60 = $1.44 per audio hour, so $1,440 per 1,000 audio hours, after the free 60 minutes a month.
How the value follows from the source: 60 free audio minutes a month at $0.024 a minute is $1.44.
How the value follows from the source: $0.024 per audio minute x 60 x 1,000.
Streaming speech recognition lets you stream audio to Cloud Speech-to-Text and receive a stream speech recognition results in real time as the audio is processed.
Streaming is available over gRPC only.
The pricing page has no separate row for live audio, so no streaming rate is stated.