ElevenLabs Scribe (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; AI agents and automation - an agent-ready surface (MCP / llms.txt)

Pricing model

Hybrid (base + usage) [2]elevenlabs.io/pricing/api“Scribe v1/v2: $0.22 per hour. Scribe v2 Realtime: $0.39 per hour. Entity Detection add-on: $0.070 per hour. Keyterm Prompting add-on: $0.050 per hour.”elevenlabs.io/pricing/api“Starter $6/month: 4.5 hours Scribe v1/v2, 2.5 hours Scribe v2 Realtime; Creator $22/month: 27 hours / 15 hours; Pro $99/month: 100 hours / 56 hours”

Published pricing

✓ Yes [3]elevenlabs.io/pricing/api“Scribe v1/v2: $0.22 per hour. Entity Detection: $0.070 per hour. Keyterm Prompting: $0.050 per hour. Scribe v2 Realtime: $0.39 per hour.”

Free tier

✓ Yes [4]elevenlabs.io/pricing“The Free plan offers 10k credits per month with access to Text to Speech, Speech to Text, Sound Effects, Voice Design, Music, Productions, Image & Video”elevenlabs.io/pricing/api“Free plan includes Scribe v1/v2: 4 hrs 30 min; Scribe v2 Realtime: 2 hrs 30 min included per month.”

Free tier details

Free plan includes 4 hours 30 minutes/month of Scribe v1/v2 transcription and 2 hours 30 minutes/month of Scribe v2 Realtime transcription at no cost (recurring monthly allowance, shared with other platform features via the 10,000 credit pool).

Self-serve signup

✓ Yes

Requires sales call

✗ No

Enterprise plan

✓ Yes [5]elevenlabs.io/pricing/api“Enterprise: Custom terms available”

• Real-time streaming
• Speaker diarization
• PII redaction

Supported actions

transcribe_batch, transcribe_streaming, speaker_diarization, language_detection, word_timestamps, character_timestamps, entity_detection, entity_redaction, keyterm_prompting, dynamic_audio_tagging, no_verbatim_mode, multichannel_processing, webhook_delivery, voice_activity_detection, manual_commit_control

Regions

US, EU, India, Singapore [6]elevenlabs.io/docs/overview/administration/data-residency“ElevenLabs offers data residency in three jurisdictions: EU (api.eu.residency.elevenlabs.io), India (api.in.residency.elevenlabs.io), Singapore (api.sg.residency.elevenlabs.io)”

Languages

Afrikaans, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Cantonese, Catalan, Central Kurdish, Chichewa, Chinese (Mandarin), Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Fulah, Galician, Ganda, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Igbo, Indonesian, Irish, Italian, Japanese, Javanese, Kabuverdianu, Kannada, Kazakh, Khmer, Korean, Kyrgyz, Lao, Latvian, Lingala, Lithuanian, Luo, Luxembourgish, Macedonian, Malay, Malayalam, Maltese, Maori, Marathi, Mongolian, Nepali, Northern Sotho, Norwegian, Occitan, Oriya, Pashto, Pedi, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Shona, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tajik, Tamil, Telugu, Thai, Turkish, Ukrainian, Umbundu, Urdu, Uzbek, Vietnamese, Welsh, Wolof, Xhosa, Zulu [7]elevenlabs.io/blog/introducing-scribe-v2“Compliance certifications: SOC 2, ISO 27001, PCI DSS L1, HIPAA, GDPR”elevenlabs.io/speech-to-text“The page enumerates 99 distinct languages with individual pages, including Afrikaans, Amharic, Arabic, Armenian, Assamese, Asturian, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Burmese, Cantonese, Catalan...”

Input types

audio/aac, audio/aiff, audio/ogg, audio/mpeg (MP3), audio/opus, audio/wav, audio/flac, audio/m4a, audio/webm, video/mp4, video/avi, video/mkv, video/quicktime (MOV), video/wmv, video/x-flv, video/mpeg, video/3gpp, file upload (up to 3 GB), cloud storage URL (up to 2 GB), YouTube URL, TikTok URL, WebSocket PCM stream (8–48 kHz), WebSocket μ-law stream (ulaw_8000) [8]elevenlabs.io/docs/overview/capabilities/speech-to-text“Audio formats: AAC, AIFF, OGG, MP3, OPUS, WAV, FLAC, M4A, WebM. Video formats: MP4, AVI, MKV, MOV, WMV, FLV, WebM, MPEG, 3GPP”

Output types

JSON (word-level timestamps, speaker IDs, confidence scores), plain text, SRT, DOCX, HTML, PDF, segmented JSON, partial_transcript (streaming), committed_transcript (streaming), committed_transcript_with_timestamps (streaming)

Webhooks

✓ Yes [9]elevenlabs.io/docs/overview/capabilities/speech-to-text“Webhooks: Asynchronous results can be sent to webhooks configured in webhook settings in the UI”

Sandbox / test mode

✗ No [10]elevenlabs.io/pricing“No dedicated sandbox or test environment mentioned; free plan provides live environment access only.”

SDK languages

Python, Node.js, Swift, Kotlin, Flutter [11]elevenlabs.io/docs/api-reference/speech-to-text/convert“The documentation provides code examples in TypeScript/JavaScript, Python, Go, Ruby, Java, PHP, C#, Swift”

MCP server

✓ Yes [12]elevenlabs.io/blog/introducing-elevenlabs-mcp“The ElevenLabs MCP server is an abstraction over the ElevenLabs API to provide a large language model with context to access the full ElevenLabs AI audio platform”

SOC 2

SOC 2 Type II [13]compliance.elevenlabs.io/resources“ElevenLabs has completed 2025 SOC 2 Type 2 + HIPAA Report Final”elevenlabs.io/docs/overview/administration/data-residency“ElevenLabs maintains SOC2 certification, demonstrating our commitment to high standards for security, availability and confidentiality.”

HIPAA

✓ Yes [14]elevenlabs.io/enterprise“ElevenLabs offers HIPAA-eligible configurations for enterprise customers when Zero Retention Mode is enabled with a Business Associate Agreement.”elevenlabs.io/docs/overview/capabilities/speech-to-text“HIPAA-compliant deployments require contacting ElevenLabs Sales to sign a Business Associate Agreement (BAA) agreement”

GDPR

✓ Yes [15]elevenlabs.io/docs/overview/administration/data-residency“GDPR Alignment: Our platform and practices are designed to align with applicable GDPR requirements”

ISO 27001

✓ Yes [16]compliance.elevenlabs.io/resources“ElevenLabs has ISO 27001/17/18, ISO 27701, and ISO 42001 certificates”elevenlabs.io/blog/introducing-scribe-v2“Compliance certifications: SOC 2, ISO 27001, PCI DSS L1, HIPAA, GDPR”

PCI DSS

✓ Yes [17]compliance.elevenlabs.io/resources“ElevenLabs is SOC 2 Type II, ISO 27001, and PCI DSS Level 1 certified”elevenlabs.io/blog/introducing-scribe-v2“Compliance certifications: SOC 2, ISO 27001, PCI DSS L1, HIPAA, GDPR”

Published SLA

✗ No [18]elevenlabs.io/enterprise“Custom service-level agreements are available for mission-critical workloads”

Rate limits

Concurrency for Scribe v1/v2 batch: min(4, round_up(audio_duration_secs/480)). Files over 8 minutes chunked into 4 parallel segments. Scribe v2 Realtime: 30+ concurrent streams on Business plans; enterprise plans include elevated limits. Response headers expose current-concurrent-requests and maximum-concurrent-requests. HTTP 429 returned on rate_limit_exceeded or concurrent_limit_exceeded. [19]elevenlabs.io/docs/overview/capabilities/speech-to-text“Concurrency = min(4, round_up(audio_duration_secs/480)). Files over 8 minutes are internally chunked into 4 segments for parallel processing”

Known restrictions

Maximum file size: 3 GB (file upload) or 2 GB (cloud storage URL), Maximum audio duration: 10 hours (standard), 1 hour (multichannel), Minimum audio duration: 100ms, Maximum channels in multichannel mode: 5, Maximum speakers for diarization: 32, Maximum keyterms: 1,000 per request (batch); 50 keyterms (realtime), Keyterm max length: under 50 characters, max 5 words (batch); up to 20 characters (realtime), Scribe v1 deprecated, removal July 9 2026, Zero Retention Mode (enable_logging=false) is enterprise-only, Data residency (EU, India, Singapore) is enterprise-only feature, HIPAA support requires BAA with ElevenLabs Sales and Zero Retention Mode enabled, Speaker diarization not available on Scribe v2 Realtime, Dual channel not supported on Scribe v2 Realtime, Entity detection and redaction incur additional cost; speaker role detection also incurs additional cost [20]elevenlabs.io/docs/overview/models“Scribe v1: Deprecated and will be removed July 9th, 2026”elevenlabs.io/docs/overview/capabilities/speech-to-text“Maximum file size: 3 GB. Maximum duration: 10 hours (standard), 1 hour (multichannel). Multi-channel mode: Up to 5 channels. Max speakers: 32 for diarization prediction”

• Docs
• API reference
• llms.txt
• Changelog
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://api.elevenlabs.io

Version

v1

Versioning

url

Stability

ga

Auth methods

api_key

Idempotency keys

✗ No

Error format

vendor-specific

Webhook signing

hmac

SDKs

• Python elevenlabs · repo
• Node.js @elevenlabs/elevenlabs-js · repo
• Swift · repo
• Kotlin io.elevenlabs:elevenlabs-android · repo
• Flutter elevenlabs_agents · repo

• Auth docs
• Quickstart
• Webhook events
• Deprecation policy

Launched

2025-02-26

GA

2025-02-26

Notable customers

Revolut, Klarna, Washington Post, Deutsche Telekom, HarperCollins

• 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

• Speechmatics

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

  Usage · free tier · public pricing · self-serve

ElevenLabs Scribe (Speech to Text) alternatives · ElevenLabs Scribe (Speech to Text) vs Azure AI 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: elevenlabs.io · elevenlabs.io
2. ↑Pricing model: elevenlabs.io · elevenlabs.io
3. ↑Published pricing: elevenlabs.io
4. ↑Free tier: elevenlabs.io · elevenlabs.io
5. ↑Enterprise plan: elevenlabs.io
6. ↑Regions: elevenlabs.io
7. ↑Languages: elevenlabs.io · elevenlabs.io
8. ↑Input types: elevenlabs.io
9. ↑Webhooks: elevenlabs.io
10. ↑Sandbox: elevenlabs.io
11. ↑SDK languages: elevenlabs.io
12. ↑MCP server: elevenlabs.io
13. ↑SOC 2: compliance.elevenlabs.io · elevenlabs.io
14. ↑HIPAA: elevenlabs.io · elevenlabs.io
15. ↑GDPR: elevenlabs.io
16. ↑ISO 27001: compliance.elevenlabs.io · elevenlabs.io
17. ↑PCI DSS: compliance.elevenlabs.io · elevenlabs.io
18. ↑Published SLA: elevenlabs.io
19. ↑Rate limits: elevenlabs.io
20. ↑Known restrictions: elevenlabs.io · elevenlabs.io

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

1. 2026-06-21 Capabilities: {} → {"pii_redaction":true,"real_time_streaming":true,"speaker_diarization":true}
2. 2026-06-21 Summary Md: (none) → ElevenLabs Scribe is a REST speech-to-text API supporting batch and real-time t…
3. 2026-06-21 Score Agent Friendliness: (none) → 65
4. 2026-06-21 Score Pricing Transparency: (none) → 100
5. 2026-06-21 Score Setup Speed: (none) → 85
6. 2026-06-21 Score Docs Quality: (none) → 55
7. 2026-06-21 Score Procurement Friction: (none) → 100
8. 2026-06-21 Score Trust Readiness: (none) → 80
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 Rendering: (none) → static
12. 2026-06-21 Llms Txt URL: (none) → https://elevenlabs.io/llms.txt
13. 2026-06-21 Has Structured Data: (none) → Yes
14. 2026-06-21 Robots Allows Agents: (none) → Yes
15. 2026-06-21 API Reference URL: (none) → https://elevenlabs.io/api
16. 2026-06-21 Status Page URL: (none) → https://status.elevenlabs.io
17. 2026-06-21 Changelog URL: (none) → https://elevenlabs.io/changelog
18. 2026-06-21 Docs URL: (none) → https://elevenlabs.io/docs/overview/intro
19. 2026-06-21 Llms Txt Present: (none) → Yes
20. 2026-06-21 Free Tier Details: set to Free plan includes 4 hours 30 minutes/month of Scribe v1/v2 transcription and 2…
21. 2026-06-21 Self Serve Signup: set to Yes
22. 2026-06-21 Requires Sales Call: set to No
23. 2026-06-21 Enterprise Plan Available: set to Yes
24. 2026-06-21 SOC 2: set to type_2
25. 2026-06-21 HIPAA: set to Yes
26. 2026-06-21 GDPR: set to Yes
27. 2026-06-21 ISO 27001: set to Yes
28. 2026-06-21 PCI DSS: set to Yes
29. 2026-06-21 SLA Published: set to No
30. 2026-06-21 Data Retention Policy URL: set to https://elevenlabs.io/dpa
31. 2026-06-21 Documented Rate Limits: set to Concurrency for Scribe v1/v2 batch: min(4, round_up(audio_duration_secs/480)). …
32. 2026-06-21 Source Confidence: set to high
33. 2026-06-21 Extractor: set to claude-subagent:sonnet
34. 2026-06-21 Last Verified At: set to 2026-06-21T00:00:00.000Z
35. 2026-06-21 Known Restrictions: set to Maximum file size: 3 GB (file upload) or 2 GB (cloud storage URL), Maximum audi…
36. 2026-06-21 Auth Methods: set to api_key
37. 2026-06-21 Auth Docs URL: set to https://elevenlabs.io/docs/api-reference/introduction
38. 2026-06-21 API Style: set to rest
39. 2026-06-21 Base URL: set to https://api.elevenlabs.io
40. 2026-06-21 API Version: set to v1
41. 2026-06-21 Versioning Scheme: set to url
42. 2026-06-21 Stability: set to ga
43. 2026-06-21 Deprecation Policy URL: set to https://elevenlabs.io/docs/developers/best-practices/breaking-changes-policy
44. 2026-06-21 Quickstart URL: set to https://elevenlabs.io/docs/eleven-api/guides/cookbooks/speech-to-text
45. 2026-06-21 Idempotency Supported: set to No
46. 2026-06-21 Error Format: set to vendor-specific
47. 2026-06-21 Webhook Signing: set to hmac
48. 2026-06-21 Slug: set to elevenlabs-scribe
49. 2026-06-21 Requires Verification: set to No
50. 2026-06-21 Starting Price Usd: set to 0.22

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/elevenlabs-scribe \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/elevenlabs-scribe/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 →