Scribe
Transcribes audio to text with speaker labels and word-level timings.
What it does
- Speech to text
Features 5
- Keyterm promptingSelect up to 1000 specific words or sentences for Scribe to transcribe accurately based on context.
- Dynamic audio taggingTags sound events from laughter to footsteps to enrich transcripts with context.
- Speaker & entity detectionLabels every speaker, calculates entity timestamps and redacts sensitive information from transcripts.
- Voice Activity DetectionDetects when speech starts and stops to segment speech for smoother live processing.
- Realtime transcriptionLive speech-to-text in under 150 ms across 90+ languages, built for agents and meetings.
How it compares
-
AssemblyAI Pre-recorded Speech-to-Text API
AssemblyAI Universal-3.5 Pro Mistral Voxtral Mini OpenAI GPT-4o Transcribe Cohere Transcribe ElevenLabs Scribe V2
Official documentation · 13 Oct 2026 -
Speech to Text API
Choose from live radio, your own voice, or sample audio to see side-by-side comparisons of Speechmatics vs ElevenLabs Scribe.
Official documentation · 13 Oct 2026
Sources
- Pricing
- Constraints
-
Official documentation · 2 Oct 2026
Derived from the security facts on this page, from the same source.
- Security
-
Official documentation · 2 Oct 2026
Docs: data-residency, zero-retention-mode (Enterprise, API only), SSO, SCIM, audit-logs pages. product_ids limited to products ZRM names (TTS, Voice Changer, STT, Agents). SOC2 is stated without a type so not recorded; HIPAA BAAs offered only for unspecified 'HIPAA-Eligible Services' so omitted. Training is from the Terms of Use: Content is used for training unless 'you opt out of our use of your Content for training' in the account's Data use menu (going forward only); Enterprise customers are not trained on by default. Residency: US standard, EU, India and Singapore isolated environments (India/Singapore mapped to apac); Enterprise feature. SSO/SCIM/audit logs are Enterprise. Vanta trust centre compliance.elevenlabs.io renders empty to curl.
- Sold within
-
The pricing page lists Speech to Text among the Free plan's inclusions, drawn from the plan's credits; /pricing/api shows Scribe hours included per plan. "All products draw from one shared monthly credit pool".
- Deployment
-
Inferred 2026-09-08, not read off a page: every already-decided product of type 'api-service' in this catalogue includes "saas" in its deployment list, zero exceptions, per item 198's measured cross-tab. May be incomplete if this product also offers a self-hosted or private-cloud option; not wrong either way.
- Interfaces
-
Official documentation · 12 Oct 2026
Page: 'Integrate Scribe v2 and Scribe v2 Realtime into your product with the API or SDKs'.
- Modalities
-
Official documentation · 1 Oct 2026
Page: 'Scribe v2 is the most accurate Speech to Text model' and 'Scribe v2 Realtime uses ElevenLabs' streaming-first architecture to turn live speech to text instantly'.
- Intended for
-
Pricing FAQ: 'falling well below this at scale with Enterprise plans'; SOC2/HIPAA compliance, on-premise configs; 'Speech to Text APIs and SDKs' to integrate into your product
Also from ElevenLabs
-
ElevenAgents Agent platform
Builds and runs voice AND chat agents that handle customer conversations over the phone, on the web and in chat, with enterprise integrations into CRM, payment and calendar systems.
-
ElevenLabs Text to Speech API service
Generates speech from text in a range of voices and languages, in the browser and through an API.
-
Ads Engine Application
Localizes and refreshes advertising creative across 50+ languages, with audio dubbing, image adaptation and text translation for Google Ads and Meta Ads.
-
ElevenAPI API service
Unified programmatic API for ElevenLabs' audio AI models (speech, voice, music, sound effects, dubbing, transcription), billed per usage from the shared credit pool.
-
ElevenCreative Application
AI-native creative workspace unifying voice, music, sound-effect, image and video generation with dubbing/localization, editable in a browser Studio.
-
Dubbing Application
Audio-to-audio dubbing across 90+ languages and accents that conditions on source performance (not a transcript) to preserve emotion and tone, with voice cloning.
-
ElevenCreative Flows Application
Chains image, video, voice and SFX generation into automated visual flows to create unlimited campaign variations from one template.
-
Image to Video AI Conversion Application
Creates videos from images and integrates AI voice, using a credit-based system.
-
ElevenMusic Application
Music generation, remixing and creation product ("Listen, remix, and create tracks"), built on the Music v2 engine, targeted at independent musicians.
-
Text to Sound Effects Application
Generates sound effects from text prompts, with royalty-free commercial usage rights on paid plans.
-
Studio Application
End-to-end workflow for producing audiobooks, podcasts and narrated videos, integrating Voice Library, Voice Design, Professional Voice Cloning and Eleven Music.
-
AI Voice Changer Application
Real-time and file-based voice conversion tool that changes a recorded voice while preserving its original performance.
-
ElevenLabs Voice Cloning Application
Instant and Professional voice cloning (IVC/PVC) that creates a synthetic replica of a speaker's voice.
-
Voice Design Application
Generates customized synthetic voices from text descriptions, powered by the Text to Speech v3 model.
-
Voice Isolator Application
Removes background noise, isolates vocals and removes music from audio or video recordings.
-
Speech Engine API service
A service that adds speech recognition and speech synthesis to chat agents while the developer supplies the LLM logic.
-
ElevenReader Application
Mobile and web app that reads any uploaded PDF, ePub, article or text aloud in more than 1,000 AI voices in 90+ languages, with a library of 200,000+ audiobooks and GenFM AI-hosted podcasts built from your own content.
-
Iconic Marketplace Application
Licensing marketplace where creators, developers and enterprises request AI voices of historical and cultural figures and officially licensed characters, with commercial rights on every approval.
-
Voiceover Studio Application
Single editor workflow that combines text to speech, speech to speech and sound effects into one produced voiceover.
-
GenFM Application
Feature of the ElevenReader app that uses AI co-hosts to turn your own content into a personalised podcast.
-
Reception.ai AI agent
AI phone receptionist for small and medium businesses: answers inbound calls in 70+ languages from a knowledge base, transfers to staff and books, reschedules or cancels appointments.
-
AI Speech Classifier Application
Free tool that estimates whether an uploaded audio clip was generated with ElevenLabs.
Open ElevenLabs in the directory
Something wrong here? Send a correction — quote this product id: elevenlabs-scribe.