Groq Speech-to-Text (Whisper)

Best for: Prototypes and side projects - free to start, no sales call; Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Usage-based [2]groq.com/pricing“Whisper Large v3 Turbo: $0.04 per hour transcribed. Whisper V3 Large: $0.111 per hour transcribed.”groq.com/pricing“$0.111 per hour transcribed (Whisper V3 Large); $0.04 per hour transcribed (Whisper Large v3 Turbo). Audio is billed at a minimum of 10s per request.”

Published pricing

✓ Yes [3]groq.com/pricing“Whisper Large v3 Turbo: $0.04 per hour transcribed. Whisper V3 Large: $0.111 per hour transcribed.”

Free tier

✓ Yes [4]groq.com/groqcloud“Free Plan: Build and test with community support at no cost.”console.groq.com/docs/rate-limits“whisper-large-v3 and whisper-large-v3-turbo: RPM: 20, RPD: 2,000, ASH: 7,200, ASD: 28,800”

Free tier details

Free Plan available at no cost with community support and zero-data retention option. Rate limits on free tier: 20 RPM, 2,000 RPD, 7,200 audio seconds/hour (ASH), 28,800 audio seconds/day (ASD) for Whisper models. Max file size 25 MB. No monetary charge; perpetual free access within these limits.

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [5]groq.com/groqcloud“Enterprise Plan: Custom models, regional endpoint selection, performance tier, scalable capacity, dedicated support, and LoRA fine-tunes. Pricing requires contacting sales.”

• Speech translation

Supported actions

transcribe_batch, translation_to_english, word_timestamps, segment_timestamps, language_detection, prompt_guided_transcription [6]console.groq.com/docs/speech-to-text“POST https://api.groq.com/openai/v1/audio/transcriptions (Transcription: Converts audio files into text in the original language); POST https://api.groq.com/openai/v1/audio/translations (Translation: Converts audio into English text). timestamp_granularities: word or segment-level timestamps.”

Regions

United States, Global (multi-region)

Languages

Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Cantonese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Myanmar, Nepali, Norwegian, Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, Yoruba [7]console.groq.com/docs/model/whisper-large-v3“Whisper Large v3 supports 99+ languages, making it exceptionally versatile for global applications.”openai-whisper.mintlify.app/concepts/languages“Whisper supports 99 languages total. [Full enumeration: Afrikaans, Albanian, Amharic, Arabic, Armenian, Assamese, Azerbaijani, Bashkir, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Cantonese, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Haitian Creole, Hausa, Hawaiian, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Javanese, Kannada, Kazakh, Khmer, Korean, Lao, Latin, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malagasy, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Myanmar, Nepali, Norwegian, Nynorsk, Occitan, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Sanskrit, Serbian, Shona, Sindhi, Sinhala, Slovak, Slovenian, Somali, Spanish, Sundanese, Swahili, Swedish, Tagalog, Tajik, Tamil, Tatar, Telugu, Thai, Tibetan, Turkish, Turkmen, Ukrainian, Urdu, Uzbek, Vietnamese, Welsh, Yiddish, Yoruba]”console.groq.com/docs/model/whisper-large-v3-turbo“Multilingual: Supports 99+ languages”

Input types

audio/flac, audio/mp3, audio/mp4, audio/mpeg, audio/mpga, audio/m4a, audio/ogg, audio/wav, audio/webm, file upload, URL (including Base64URL) [8]console.groq.com/docs/speech-to-text“Supported: FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, WebM. Free tier: 25 MB max. Dev tier: 100 MB max. Supports URL or direct upload.”

Output types

JSON, text, verbose_json (with word and segment timestamps) [9]console.groq.com/docs/speech-to-text“Output Formats: JSON (default), verbose_json (includes timestamps), text. When using verbose_json, responses include quality indicators: avg_logprob, compression_ratio, and no_speech_prob.”

Webhooks

✗ No

Sandbox / test mode

✗ No

SDK languages

Python, Node.js, C#, PHP [10]console.groq.com/docs/libraries“The Groq Python library provides convenient access to the Groq REST API from any Python 3.7+ application. The Groq JavaScript library provides convenient access to the Groq REST API from server-side TypeScript or JavaScript.”

MCP server

✓ Yes [11]github.com/groq/groq-mcp-server“Official Groq MCP server published by Groq at groq/groq-mcp-server. Enables access to Groq's AI models through the Model Context Protocol (MCP), including Speech: Text-to-speech synthesis and speech-to-text transcription.”

SOC 2

SOC 2 Type II [12]console.groq.com/docs/legal/customer-data-processing-addendum“Annual engagements of a qualified, independent external auditor to conduct periodic reviews of Groq's security practices against recognized audit standards, including SOC 2 Type II certification audits.”groq.com/groqcloud“SOC 2, GDPR, and HIPAA compliant”

HIPAA

✓ Yes [13]console.groq.com/docs/legal/customer-business-associate-addendum“Groq provides a Business Associate Addendum (BAA) effective October 15, 2025, that supplements its Services Agreement for customers who are HIPAA-covered entities or business associates.”groq.com/groqcloud“SOC 2, GDPR, and HIPAA compliant”

GDPR

✓ Yes [14]groq.com/groqcloud“SOC 2, GDPR, and HIPAA compliant”console.groq.com/docs/legal/customer-data-processing-addendum“The General Data Protection Regulation, Regulation (EU) 2016/679 is listed as applicable Data Protection Law. Module 2 (Controller-to-Processor) and Module 3 (Processor-to-sub-Processor) of EU SCCs apply.”

ISO 27001

– Unknown

PCI DSS

– Unknown

Published SLA

✗ No [15]groq.com/security“Visit the Groq Trust Center to learn more about our information security program, compliance posture, and supporting documentation.”console.groq.com/docs/legal/customer-data-processing-addendum“This Data Processing Addendum contains no Service Level Agreement (SLA) or uptime commitment. The document focuses exclusively on data protection, processing, and security requirements.”

Rate limits

{"free_plan": {"whisper-large-v3": "20 RPM, 2,000 RPD, 7,200 ASH, 28,800 ASD", "whisper-large-v3-turbo": "20 RPM, 2,000 RPD, 7,200 ASH, 28,800 ASD"}, "developer_plan": {"whisper-large-v3": "300 RPM, 200,000 ASH", "whisper-large-v3-turbo": "400 RPM, 400,000 ASH"}, "note": "Higher limits available for enterprise use cases"} [16]console.groq.com/docs/rate-limits“whisper-large-v3 and whisper-large-v3-turbo: RPM: 20, RPD: 2,000, ASH (Audio Seconds per Hour): 7,200, ASD (Audio Seconds per Day): 28,800”console.groq.com/docs/models“whisper-large-v3: Rate limits: 200K ASH, 300 RPM, Max file size: 100 MB. whisper-large-v3-turbo: Rate limits: 400K ASH, 400 RPM”

Known restrictions

Free tier: 25 MB max file size per request, Developer tier: 100 MB max file size per request, Minimum billable duration: 10 seconds per request, Single audio track only (first track used from multi-track files), Translation endpoint outputs English only, whisper-large-v3-turbo does not support translation endpoint, Audio shorter than 30 seconds is padded with silence (minimum 0.01 seconds), BAA (HIPAA) excludes beta, alpha, free tier, and experimental features, distil-whisper-large-v3-en was deprecated and sunset on August 23, 2025; migrate to whisper-large-v3-turbo [17]console.groq.com/docs/deprecations“distil-whisper-large-v3-en was sunset on 08/23/25; migrate to whisper-large-v3-turbo”console.groq.com/docs/speech-to-text“Free tier: 25 MB max. Dev tier: 100 MB max. Minimum billable: 10 seconds. Single audio track only (first track transcribed from multi-track files). Translation endpoint only supports English output.”

• Docs
• API reference
• Changelog
• Status page

Docs rendering: static

API style

rest

Base URL

https://api.groq.com/openai/v1

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Error format

vendor-specific

Rate limit

20 / minute

SDKs

• Python groq · repo
• Node.js groq-sdk · repo
• C# jgravelle.GroqAPILibrary · repo
• PHP lucianotonet/groq-php · repo

• Auth docs
• Quickstart
• Deprecation policy

Launched

2024-06-24

GA

2024-06-24

Notable customers

IBM, PGA of America, Stats Perform, GPTZero, StackAI, Mem0

• 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

• Google Cloud Speech-to-Text

  "Accurate voice typing and transcription powered by Gemini."

  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

Groq Speech-to-Text (Whisper) alternatives · Groq Speech-to-Text (Whisper) 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: console.groq.com
2. ↑Pricing model: groq.com · groq.com
3. ↑Published pricing: groq.com
4. ↑Free tier: groq.com · console.groq.com
5. ↑Enterprise plan: groq.com
6. ↑Supported actions: console.groq.com
7. ↑Languages: console.groq.com · openai-whisper.mintlify.app · console.groq.com
8. ↑Input types: console.groq.com
9. ↑Output types: console.groq.com
10. ↑SDK languages: console.groq.com
11. ↑MCP server: github.com
12. ↑SOC 2: console.groq.com · groq.com
13. ↑HIPAA: console.groq.com · groq.com
14. ↑GDPR: groq.com · console.groq.com
15. ↑Published SLA: groq.com · console.groq.com
16. ↑Rate limits: console.groq.com · console.groq.com
17. ↑Known restrictions: console.groq.com · console.groq.com

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

1. 2026-06-21 Capabilities: {} → {"translation":true}
2. 2026-06-21 Summary Md: (none) → Groq Speech-to-Text runs OpenAI-compatible Whisper endpoints (large-v3 and larg…
3. 2026-06-21 Score Pricing Transparency: (none) → 100
4. 2026-06-21 Score Agent Friendliness: (none) → 40
5. 2026-06-21 Score Setup Speed: (none) → 85
6. 2026-06-21 Score Docs Quality: (none) → 45
7. 2026-06-21 Score Procurement Friction: (none) → 100
8. 2026-06-21 Score Trust Readiness: (none) → 55
9. 2026-06-21 Best For: (none) → Prototypes and side projects - free to start, no sales call, Regulated or enter…
10. 2026-06-21 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
11. 2026-06-21 Has Structured Data: (none) → No
12. 2026-06-21 Robots Allows Agents: (none) → Yes
13. 2026-06-21 API Reference URL: (none) → https://groq.com/groqcloud
14. 2026-06-21 Status Page URL: (none) → https://status.groq.com
15. 2026-06-21 Changelog URL: (none) → https://groq.com/changelog
16. 2026-06-21 Docs URL: (none) → https://console.groq.com/docs/overview
17. 2026-06-21 Rendering: (none) → static
18. 2026-06-21 Llms Txt Present: (none) → No
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 Free Plan available at no cost with community support and zero-data retention o…
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 SLA Published: set to No
29. 2026-06-21 Data Retention Policy URL: set to https://console.groq.com/docs/your-data
30. 2026-06-21 Documented Rate Limits: set to {"free_plan":{"whisper-large-v3":"20 RPM, 2,000 RPD, 7,200 ASH, 28,800 ASD","wh…
31. 2026-06-21 Rate Limit Requests: set to 20
32. 2026-06-21 Rate Limit Window: set to minute
33. 2026-06-21 Known Restrictions: set to Free tier: 25 MB max file size per request, Developer tier: 100 MB max file siz…
34. 2026-06-21 Auth Methods: set to api_key
35. 2026-06-21 Auth Docs URL: set to https://console.groq.com/docs/quickstart
36. 2026-06-21 API Style: set to rest
37. 2026-06-21 Base URL: set to https://api.groq.com/openai/v1
38. 2026-06-21 Versioning Scheme: set to url
39. 2026-06-21 Stability: set to ga
40. 2026-06-21 Deprecation Policy URL: set to https://console.groq.com/docs/deprecations
41. 2026-06-21 Quickstart URL: set to https://console.groq.com/docs/quickstart
42. 2026-06-21 Idempotency Supported: set to No
43. 2026-06-21 Error Format: set to vendor-specific
44. 2026-06-21 Requires Verification: set to No
45. 2026-06-21 Starting Price Usd: set to 0.04
46. 2026-06-21 Slug: set to groq-speech-to-text
47. 2026-06-21 Free Tier Limit: set to 2000 audio requests/day (RPD); 7200 audio seconds/hour (ASH); 28800 audio secon…
48. 2026-06-21 Launched At: set to 2024-06-24
49. 2026-06-21 GA Date: set to 2024-06-24
50. 2026-06-21 Notable Customers: set to IBM, PGA of America, Stats Perform, GPTZero, StackAI, Mem0

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/groq-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/groq-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 →