Google Cloud Speech-to-Text

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; Teams needing broad API coverage out of the box

Pricing model

Usage-based [2]cloud.google.com/blog/products/ai-machine-learning/google-cloud-speech-to-text-v2-api“Standard (Real-time/Batch): $0.016 per minute (down from $0.024)”cloud.google.com/speech-to-text/pricing“Speech-to-Text is priced based on the amount of audio successfully processed by the service each month, measured in increments of one second.”

Published pricing

✓ Yes [3]cloud.google.com/speech-to-text/pricing“Google has lowered the cost of real-time and batch transcription from $0.024 per minute to $0.016 per minute.”cloud.google.com/blog/products/ai-machine-learning/google-cloud-speech-to-text-v2-api“Standard volume tiers allow costs as low as $0.004 per minute”

Free tier

✓ Yes [4]brasstranscripts.com/blog/google-cloud-speech-to-text-pricing-2025-gcp-integration-costs“60 minutes/month ongoing free tier for Speech-to-Text”cloud.google.com/speech-to-text/pricing“All users can send up to 60 minutes of audio to Cloud Speech-to-Text for free each month.”

Free tier details

60 minutes of audio per month free (recurring monthly allowance); applies to both streaming and batch recognition across V1 and V2 APIs.

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes

• Real-time streaming
• Speaker diarization
• Medical transcription

Supported actions

transcribe_synchronous, transcribe_batch, transcribe_streaming, speaker_diarization, automatic_punctuation, spoken_punctuation, spoken_emoji, profanity_filtering, word_timestamps, word_confidence_scores, language_detection, model_adaptation, custom_vocabulary_phrase_sets, custom_classes, srt_caption_generation, webvtt_caption_generation, recognizer_management, dynamic_batch_recognition [5]docs.cloud.google.com/speech-to-text/docs/concepts“Transcribe long audio files ... Transcribe streaming audio ... Detect different speakers ... Automatically detect spoken language ... Enable automatic punctuation ... Enable spoken punctuation and spoken emoji ... Enable profanity filtering ... Generate WebVTT & SRT Captions ... Improve transcription with model adaptation”

Regions

global, us (US North America multi-region), eu (Europe multi-region), europe-west1, europe-west2, europe-west3, europe-west4, us-central1, asia-southeast1, asia-northeast1, asia-south1, northamerica-northeast1 [6]docs.cloud.google.com/speech-to-text/docs/locations“In Cloud Speech-to-Text API V2, there are different availabilities in different regions. To understand the availabilities, use the Locations API.”docs.cloud.google.com/speech-to-text/docs/speech-to-text-supported-languages“asia-northeast1, asia-south1, asia-southeast1, eu, europe-west2, europe-west3, europe-west4, global, northamerica-northeast1, us, us-central1”

Languages

190+ language-region variants (BCP-47 codes) including: Afrikaans (af-ZA), Albanian (sq-AL), Amharic (am-ET), Arabic (20+ regional variants: ar-AE, ar-BH, ar-DZ, ar-EG, ar-IL, ar-IQ, ar-JO, ar-KW, ar-LB, ar-LY, ar-MA, ar-MR, ar-OM, ar-PS, ar-QA, ar-SA, ar-SY, ar-TN, ar-YE), Armenian (hy-AM), Assamese (as-IN), Azerbaijani (az-AZ), Bangla/Bengali (bn-BD, bn-IN), Basque (eu-ES), Bosnian (bs-BA), Bulgarian (bg-BG), Burmese (my-MM), Catalan (ca-ES), Chinese Cantonese (yue-Hant-HK), Chinese Mandarin (zh, zh-TW), Croatian (hr-HR), Czech (cs-CZ), Danish (da-DK), Dutch (nl-BE, nl-NL), English (en-AU, en-CA, en-GB, en-GH, en-HK, en-IE, en-IN, en-KE, en-NG, en-NZ, en-PH, en-PK, en-SG, en-TZ, en-US, en-ZA), Estonian (et-EE), Filipino (fil-PH), Finnish (fi-FI), French (fr-BE, fr-CA, fr-CH, fr-FR), Galician (gl-ES), Georgian (ka-GE), German (de-AT, de-CH, de-DE), Greek (el-GR), Gujarati (gu-IN), Hausa (ha-NG), Hebrew (iw-IL), Hindi (hi-IN), Hungarian (hu-HU), Icelandic (is-IS), Indonesian (id-ID), Italian (it-CH, it-IT), Japanese (ja-JP), Javanese (jv-ID), Kannada (kn-IN), Kazakh (kk-KZ), Khmer (km-KH), Korean (ko-KR), Lao (lo-LA), Latvian (lv-LV), Lithuanian (lt-LT), Macedonian (mk-MK), Malay (ms-MY), Malayalam (ml-IN), Marathi (mr-IN), Mongolian (mn-MN), Nepali (ne-NP), Norwegian (nb-NO), Pashto (ps-AF), Persian (fa-IR), Polish (pl-PL), Portuguese (pt-BR, pt-PT), Punjabi (pa-Guru-IN), Romanian (ro-RO), Russian (ru-RU), Serbian (sr-RS), Sinhala (si-LK), Slovak (sk-SK), Slovenian (sl-SI), Somali (so-SO), Spanish (es-AR, es-BO, es-CL, es-CO, es-CR, es-CU, es-DO, es-EC, es-ES, es-GT, es-HN, es-MX, es-NI, es-PA, es-PE, es-PR, es-PY, es-SV, es-US, es-UY, es-VE), Sundanese (su-ID), Swahili (sw-KE, sw-TZ), Swedish (sv-SE), Tamil (ta-IN, ta-LK, ta-MY, ta-SG), Telugu (te-IN), Thai (th-TH), Turkish (tr-TR), Ukrainian (uk-UA), Urdu (ur-IN, ur-PK), Uzbek (uz-UZ), Vietnamese (vi-VN), Xhosa (xh-ZA), Yoruba (yo-NG), Zulu (zu-ZA) [7]docs.cloud.google.com/speech-to-text/docs/speech-to-text-supported-languages“Cloud Speech-to-Text V2 supports 190+ language variants across multiple regions and models. Language is specified within a recognition request's languageCodes parameter.”docs.cloud.google.com/speech-to-text/docs/speech-to-text-supported-languages“This page lists all languages supported by Cloud Speech-to-Text.”

Input types

audio/flac (FLAC), audio/l16 (LINEAR16 PCM), audio/mulaw (MULAW / μ-law), audio/mpeg (MP3), audio/amr (AMR narrowband, 8000 Hz), audio/amr-wb (AMR-WB wideband, 16000 Hz), audio/ogg; codecs=opus (OGG_OPUS), audio/speex (SPEEX_WITH_HEADER_BYTE, 16000 Hz), video/webm; codecs=opus (WEBM_OPUS), WAV (with LINEAR16 or MULAW encoding), Cloud Storage URI (gs://), local file upload (≤10 MB), live streaming via WebSocket/gRPC

Output types

JSON (transcription results with confidence scores), plain text transcript, word-level timestamps, word confidence scores, speaker diarization tags, SRT captions, WebVTT captions, Cloud Storage file output (TranscriptOutputConfig)

Webhooks

✗ No [8]docs.cloud.google.com/speech-to-text/docs/overview“Asynchronous requests use long-running operations that require periodic polling for results rather than push-based notifications.”

Sandbox / test mode

✗ No [9]cloud.google.com/speech-to-text/pricing“All users can send up to 60 minutes of audio to Cloud Speech-to-Text for free each month. — this is a live-environment free tier, not a dedicated sandbox environment.”

SDK languages

Python, Node.js, Java, Go, C#, PHP, Ruby, C++ [10]github.com/googleapis/google-cloud-cpp“google-cloud-cpp speech — official C++ client library for Google Cloud APIs including Speech-to-Text”docs.cloud.google.com/speech-to-text/docs/libraries“Client libraries make it easier to access Google Cloud APIs from a supported language ... C# ... Go ... Java ... Node.js ... PHP ... Python ... Ruby”

MCP server

✗ No [11]docs.cloud.google.com/mcp/supported-products“Google Cloud Speech-to-Text is not listed as a supported product for Google Cloud MCP servers.”

SOC 2

SOC 2 Type II [12]cloud.google.com/security/compliance/services-in-scope“SOC 1, 2, 3 Reports ... Speech recognition and transcription across 125 languages”cloud.google.com/security/compliance/soc-2“Below are Google Cloud services that are in scope for SOC 2.”

HIPAA

✓ Yes [13]cloud.google.com/security/compliance/hipaa“If you are using Cloud Speech-to-Text, and you have entered into a BAA with Google covering any PHI obligations under HIPAA, then you should not opt into the data logging program.”cloud.google.com/terms/hipaa-baa“The Google Cloud BAA covers Google Cloud's entire infrastructure (all regions, all zones, all network paths, all points of presence), and the services listed below.”

GDPR

✓ Yes [14]cloud.google.com/security/compliance“Google Cloud supports GDPR compliance requirements.”

ISO 27001

✓ Yes [15]cloud.google.com/security/compliance/services-in-scope“ISO 27001, 27017, 27018 ... Speech-to-Text”cloud.google.com/security/compliance/iso-27001“Google Cloud is ISO/IEC 27001:2022 compliant”

PCI DSS

✓ Yes [16]cloud.google.com/security/compliance/services-in-scope“PCI DSS Certification ... Speech recognition and transcription across 125 languages”

Published SLA

✓ Yes [17]cloud.google.com/speech-to-text/sla“Google Cloud Speech-to-Text provides a monthly uptime percentage of >= 99.9%. If Google does not meet the SLO, and if the Customer meets its obligations under this SLA, the Customer will be eligible to receive Financial Credits.”

Rate limits

V2 API: Resource requests 100/60s; Operation requests 150/60s; Synchronous recognition 300/60s; Batch recognition 150/60s (all per region). V1 API: 900 recognition requests per 60 seconds per project (global). Daily audio processing limit: 480 hours per day. Synchronous audio max: ~1 min. Streaming session max: ~5 min. Async audio max: ~480 min. Local file max: 10 MB. [18]docs.cloud.google.com/speech-to-text/docs/v1/quotas“Recognition requests: 900 per 60 seconds ... Adaptation resource requests: 10 per 60 seconds ... 480 hours of audio per day”docs.cloud.google.com/speech-to-text/docs/quotas“Resource requests: 100 per 60 seconds; Operation requests: 150 per 60 seconds; Synchronous recognition: 300 per 60 seconds; Batch recognition: 150 per 60 seconds”

Known restrictions

Synchronous recognition limited to ~1 minute of audio, Streaming sessions limited to ~5 minutes; session must be restarted for longer audio, Asynchronous audio over ~1 minute must be referenced via a Cloud Storage URI (gs://), Local file upload limit: 10 MB per request; no limit for Cloud Storage URIs, Multi-channel audio billed per channel (stereo = 2x rate), Maximum 5,000 phrases per adaptation request; 100,000 total characters; 100 characters per phrase, 900 recognition requests per 60 seconds per project on V1 (soft quota, adjustable), 480 hours of audio per day (daily quota, resets midnight PST/PDT), Custom speech model training is allowlist-only feature, No native webhook/push-notification for async job completion; polling or Cloud Storage triggers required, HIPAA users must not opt into the data logging program, Medical models (medical_conversation, medical_dictation) are V1 API only [19]costbench.com/software/ai-transcription-apis/google-speech-to-text/“Multi-channel audio is billed per channel, effectively doubling stereo recordings to $0.032/min”docs.cloud.google.com/speech-to-text/quotas“Synchronous: ~1 Minute ... Asynchronous: ~480 Minutes (audio over ~1 minute requires Cloud Storage URI) ... Streaming: ~5 Minutes ... Local files: 10 MB maximum per request”

• Docs
• Status page

Docs rendering: static

API style

rest

Base URL

https://speech.googleapis.com

Version

v2

Versioning

url

Stability

ga

Auth methods

oauth2, api_key

Error format

vendor-specific (Google API error JSON: {error: {code, message, status}})

Rate limit

300 / minute

SDKs

• Python google-cloud-speech · repo
• Node.js @google-cloud/speech · repo
• Java com.google.cloud:google-cloud-speech · repo
• Go cloud.google.com/go/speech/apiv2 · repo
• C# Google.Cloud.Speech.V2 · repo
• PHP google/cloud/speech · repo
• Ruby google-cloud-speech · repo
• C++ google-cloud-cpp speech · repo

• Auth docs
• Quickstart
• Deprecation policy

Launched

2016-01-01

GA

2017-04-18

Notable customers

HubSpot, InteractiveTel, Embodied, iGenius, LogMeIn

• ElevenLabs Scribe (Speech to Text)

  "Scribe v2 is the most accurate Speech to Text model" offering "real-time Speech to Text in under 150 ms" across "90+ languages."

  Hybrid · free tier · public pricing · self-serve

• Azure AI Speech to Text

  "Azure Speech in Foundry Tools provides speech to text, text to speech, and other capabilities through a Microsoft Foundry resource. You can transcribe speech to text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and conduct live AI voice conversations."

  Usage · free tier · public pricing · self-serve

• Amazon Transcribe

  "Amazon Transcribe is an automatic speech recognition service that uses machine learning models to convert audio to text. You can use Amazon Transcribe as a standalone transcription service or to add speech-to-text capabilities to any application."

  Usage · free tier · public pricing · self-serve

• IBM watsonx Speech to Text

  "IBM Watson® Speech to Text technology enables fast and accurate speech transcription in multiple languages for a variety of use cases, including but not limited to customer self-service, agent assistance and speech analytics."

  Usage · free tier · public pricing · self-serve

• AssemblyAI

  "Voice AI infrastructure for developers building products that transcribe, understand, and act on speech."

  Usage · public pricing · self-serve

• Speechmatics

  "Low-latency speech-to-text for multilingual, multi-speaker conversations."

  Usage · free tier · public pricing · self-serve

Google Cloud Speech-to-Text alternatives · Google Cloud Speech-to-Text vs ElevenLabs Scribe (Speech to Text) · All Speech-to-Text & Transcription APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: cloud.google.com
2. ↑Pricing model: cloud.google.com · cloud.google.com
3. ↑Published pricing: cloud.google.com · cloud.google.com
4. ↑Free tier: brasstranscripts.com · cloud.google.com
5. ↑Supported actions: docs.cloud.google.com
6. ↑Regions: docs.cloud.google.com · docs.cloud.google.com
7. ↑Languages: docs.cloud.google.com · docs.cloud.google.com
8. ↑Webhooks: docs.cloud.google.com
9. ↑Sandbox: cloud.google.com
10. ↑SDK languages: github.com · docs.cloud.google.com
11. ↑MCP server: docs.cloud.google.com
12. ↑SOC 2: cloud.google.com · cloud.google.com
13. ↑HIPAA: cloud.google.com · cloud.google.com
14. ↑GDPR: cloud.google.com
15. ↑ISO 27001: cloud.google.com · cloud.google.com
16. ↑PCI DSS: cloud.google.com
17. ↑Published SLA: cloud.google.com
18. ↑Rate limits: docs.cloud.google.com · docs.cloud.google.com
19. ↑Known restrictions: costbench.com · docs.cloud.google.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-21 Capabilities: {} → {"medical":true,"real_time_streaming":true,"speaker_diarization":true}
2. 2026-06-21 Summary Md: (none) → Google Cloud Speech-to-Text is a REST API from Google Cloud that converts audio…
3. 2026-06-21 Score Setup Speed: (none) → 85
4. 2026-06-21 Score Pricing Transparency: (none) → 100
5. 2026-06-21 Score Docs Quality: (none) → 15
6. 2026-06-21 Score Procurement Friction: (none) → 100
7. 2026-06-21 Score Trust Readiness: (none) → 100
8. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
9. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
10. 2026-06-21 Score Agent Friendliness: (none) → 20
11. 2026-06-21 Robots Allows Agents: (none) → Yes
12. 2026-06-21 Status Page URL: (none) → https://status.cloud.google.com
13. 2026-06-21 Docs URL: (none) → https://docs.cloud.google.com/
14. 2026-06-21 Rendering: (none) → static
15. 2026-06-21 Has Structured Data: (none) → No
16. 2026-06-21 Llms Txt Present: (none) → No
17. 2026-06-21 MCP Server Available: set to No
18. 2026-06-21 Pricing Model: set to usage_based
19. 2026-06-21 Has Published Pricing: set to Yes
20. 2026-06-21 Free Tier Available: set to Yes
21. 2026-06-21 Free Tier Details: set to 60 minutes of audio per month free (recurring monthly allowance); applies to bo…
22. 2026-06-21 Self Serve Signup: set to Yes
23. 2026-06-21 Requires Sales Call: set to No
24. 2026-06-21 Enterprise Plan Available: set to Yes
25. 2026-06-21 SOC 2: set to type_2
26. 2026-06-21 HIPAA: set to Yes
27. 2026-06-21 GDPR: set to Yes
28. 2026-06-21 ISO 27001: set to Yes
29. 2026-06-21 PCI DSS: set to Yes
30. 2026-06-21 SLA Published: set to Yes
31. 2026-06-21 SLA URL: set to https://cloud.google.com/speech-to-text/sla
32. 2026-06-21 Data Retention Policy URL: set to https://docs.cloud.google.com/speech-to-text/docs/v1/data-usage-faq
33. 2026-06-21 Documented Rate Limits: set to V2 API: Resource requests 100/60s; Operation requests 150/60s; Synchronous reco…
34. 2026-06-21 Rate Limit Requests: set to 300
35. 2026-06-21 Rate Limit Window: set to minute
36. 2026-06-21 Known Restrictions: set to Synchronous recognition limited to ~1 minute of audio, Streaming sessions limit…
37. 2026-06-21 Auth Methods: set to oauth2, api_key
38. 2026-06-21 Auth Docs URL: set to https://cloud.google.com/speech-to-text/docs/authentication
39. 2026-06-21 API Style: set to rest
40. 2026-06-21 Base URL: set to https://speech.googleapis.com
41. 2026-06-21 API Version: set to v2
42. 2026-06-21 Versioning Scheme: set to url
43. 2026-06-21 Stability: set to ga
44. 2026-06-21 Deprecation Policy URL: set to https://cloud.google.com/terms/deprecation
45. 2026-06-21 Error Format: set to vendor-specific (Google API error JSON: {error: {code, message, status}})
46. 2026-06-21 Requires Verification: set to No
47. 2026-06-21 Starting Price Usd: set to 0.016
48. 2026-06-21 Price Basis: set to minute
49. 2026-06-21 Free Tier Limit: set to 60 minutes/month
50. 2026-06-21 Launched At: set to 2016-01-01

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/google-speech-to-text \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/google-speech-to-text/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →