Skip to content
SPECIFICTION
Get listed

Google Cloud Speech-to-Text

cloud.google.com

From $0.02/mo Free plan WebAPISelf-hosted
Visit cloud.google.com
Spec score 8.8 #9 of 46 in AI transcription tools

What it is

Google Cloud Speech-to-Text converts audio into text and provides APIs for adding speech recognition to applications. It offers synchronous, asynchronous, and streaming recognition for post-processing, periodic, or real-time results, and lists support for 85+ languages and variants. Model adaptation lets users provide hints for domain-specific terms, rare words, and phrases. Speaker diarization can predict which speaker produced each utterance; the service also supports multichannel recognition and says it can handle noisy audio without additional noise cancellation. Specialized models are available for voice control, phone calls, and video transcription. API v2 includes data residency, audit logging, and customer-managed encryption keys. Speech-to-Text On-Prem runs in private data centers and is offered through a sales contact. Developer access includes REST and RPC APIs, client libraries, and command-line quickstarts. Listed pricing includes Speech-to-Text V2 API standard recognition models at $0.02 a month, billed at $0.016 / 1 minute for 0–500,000 minutes, with lower rates at higher monthly volumes; V1 standard plans include 60 free minutes per month. Costs depend on duration, channel count, model, batch method, and API version, with each channel billed separately.

Spec sheet

Purpose
Speech-to-Text converts audio into text transcriptions and provides APIs for integrating speech recognition into applications.Read 3 Oct 2026 · cloud.google.com
Free plan
NoRead 20 Sep 2026 · cloud.google.com
Company
Google Inc. was officially born in August 1998, and Google’s current headquarters is in Mountain View, California.Read 3 Oct 2026 · about.google
API access
YesRead 20 Sep 2026 · cloud.google.com
Audio handling
The service supports multichannel recognition and says it can handle noisy audio without additional noise cancellation.Read 3 Oct 2026 · cloud.google.com
Billing limits
Pricing depends on audio duration, number of channels, recognition model, batch method, and API version; each channel is billed separately.Read 3 Oct 2026 · cloud.google.com
Connected service example
A Google Cloud tutorial describes using Speech-to-Text with Translation API to create localized video subtitles.Read 3 Oct 2026 · cloud.google.com
Export formats
VTT,SRTRead 20 Sep 2026 · cloud.google.com
Integration and developer access
The documentation lists REST and RPC APIs, client libraries, and command-line quickstarts.Read 3 Oct 2026 · docs.cloud.google.com
Languages
The product page states support for 85+ languages and variants.Read 3 Oct 2026 · cloud.google.com
Model adaptation
Model adaptation lets users give hints to improve recognition of domain-specific terms, rare words, and phrases.Read 3 Oct 2026 · cloud.google.com
On-premises option
Speech-to-Text On-Prem runs in customers’ private data centers and is offered through a sales contact.Read 3 Oct 2026 · cloud.google.com
Real-time and batch modes
The service supports synchronous, asynchronous, and streaming speech recognition for post-processing, periodic, or real-time results.Read 3 Oct 2026 · cloud.google.com
Security controls
Speech-to-Text API v2 supports data residency, audit logging, and customer-managed encryption keys.Read 3 Oct 2026 · cloud.google.com
Speaker diarization
The service can predict which speaker produced each utterance in a conversation.Read 3 Oct 2026 · cloud.google.com
Speaker identification
YesRead 20 Sep 2026 · cloud.google.com
Specialized models
Google offers models tuned for uses including voice control, phone calls, and video transcription.Read 3 Oct 2026 · cloud.google.com
Timestamp support
YesRead 20 Sep 2026 · cloud.google.com

Plans and prices

Speech-to-Text V2 Standard recognition $0.02 a month per 1 month / account Standard speech recognition Read 20 Sep 2026 · cloud.google.com
Speech-to-Text V2 Dynamic Batch Recognition Free per 1 month / account Dynamic batch processing Read 20 Sep 2026 · cloud.google.com
Speech-to-Text V1 Standard with data logging $0.02 a month 60 free minutes, then per 1 month / account 60 free minutes per month Read 20 Sep 2026 · cloud.google.com
Speech-to-Text V1 Standard without data logging $0.02 a month 60 free minutes, then per 1 month / account 60 free minutes per month Read 20 Sep 2026 · cloud.google.com
Medical Dictation $0.08 a month 60 free minutes, then per 1 month / account 60 free minutes per month Read 20 Sep 2026 · cloud.google.com
Medical Conversation $0.08 a month 60 free minutes, then per 1 month / account 60 free minutes per month Read 20 Sep 2026 · cloud.google.com
Speech-to-Text V1 API — Standard with data logging Free 0–60 minutes: $0.00 (Free) / 1 minute, per 1 month / account; 60 minutes and above: $0.016 / 1 minute, per 1 month / account 60 free minutes per month · standard recognition models Read 3 Oct 2026 · cloud.google.com
Speech-to-Text V1 API — Standard without data logging Free 0–60 minutes: $0.00 (Free) / 1 minute, per 1 month / account; 60 minutes and above: $0.024 / 1 minute, per 1 month / account 60 free minutes per month · standard recognition models Read 3 Oct 2026 · cloud.google.com
Speech-to-Text V2 API — Standard dynamic batch recognition Free $0.003 / 1 minute, per 1 month / account Dynamic batch · standard models · lower-urgency processing Read 3 Oct 2026 · cloud.google.com
Speech-to-Text V2 API — Standard recognition models $0.02 a month $0.016 / 1 minute, per 1 month / account for 0–500,000 minutes; lower rates apply at higher monthly volumes Per-minute usage billing · price varies by volume and model Read 3 Oct 2026 · cloud.google.com

Every Google Cloud Speech-to-Text plan and price →

Strong points and limits

Strong points

  • Lists support for 85+ languages and variants
  • Offers synchronous, asynchronous, and streaming recognition
  • Speaker diarization can label utterances by speaker
  • API v2 includes residency and audit controls
  • V1 standard plans include 60 free minutes per month

Limits

  • Each audio channel is billed separately
  • Pricing varies by duration, model, and API version
  • On-premises availability requires contacting sales

Who it suits

Speech-to-Text suits developers integrating transcription into applications or workflows that need streaming, batch, or synchronous recognition. Organizations with private data-center requirements can consider the on-premises option, which is offered through a sales contact.

Verdict

Speech-to-Text offers multiple recognition modes and developer interfaces, with model adaptation and speaker labeling among its stated capabilities. Review the applicable per-minute plan and billing variables before estimating usage costs.

Where Specifiction places it

Alternatives to Google Cloud Speech-to-TextAll alternatives →