Products
Real-time deepfake detection
Product overview
APIs
Deepfake detection
Detect synthetic audio, video, and images
Intelligence
Get structured insights and a plain-language result
Watermarking
Provenance and C2PA compliance
Identity registration
Enroll and authenticate a voice
READY-TO-USE
Meetings protection
Detect synthetic voices and faces.
Agent detection
The first System One model for AI agent detection
Deepfake detection Chrome extension
Detect deepfakes directly in your browser
IN YOUR STACK
Integrations and partners
Deployment environments
FEATURED PARTNER
Microsoft Teams
Now Microsoft Teams users can get Resemble detection in Teams in just one click.
LEARN MORE →
Research
LATEST MODELS
RAD-S1
The first System One model for AI agent detection
DETECT-World
The first world model architecture for detection
PerTh Multimodal
Imperceptible, multimodal watermarks
Intelligence
Human-readable explainability for deterministic results
Identity
Enroll and detect voice and likeness for identity matching
Models overview
FINDINGS
Benchmarks
Research articles
LATEST MODEL
RAD-S1
Introducing the first System One model for agent detection. Identify AI agents that bot detection misses.
VIEW MODEL →
Solutions
TEAMS
Fraud & Identity
Security & Risk
Trust & Safety
HR & Recruiting
USE CASE
Voice agents
Dispute & claim verification
Executive impersonation
Media watermarking
Contact center fraud
Identity verification & KYC
INDUSTRY
Telco
Marketplace
Finance
Media & entertainment
HealthTech
Public sector
ON DEMAND WEBINAR
Deepfake Fraud at Work
62% of orgs experienced a deepfake attack in the last 12 months. Learn what these attacks look like and what stops them.
VIEW ON DEMAND →
Learn
MONITOR
Deepfake Incident database
Laws & regulations
Attack vectors
RESOURCES
Blog
Case studies
Trust center
NOW AVAILABLE
2026 Political Deepfake Report
We tracked 481 incidents of AI-generated media involving politicians, governments and elections over almost a year.
DOWNLOAD →
Developers
SDKs
Docs
Discord
Status
Changelog
Builder’s Grant
Get an API key
Start free. Put real-time detection in your workflow or app now.
START FREE →
Pricing
Log in
Start free
Contact us
Contact us
Start free
Log in
Changelog
Updates and improvements to Resemble AI
May 2026
Nov 3, 2026
Resemble Detect for Microsoft Teams in the Microsoft Marketplace
Real-time audio and video deepfake detection for Teams is live in the Microsoft Marketplace, with or without a bot.
New
Resemble Meetings
Oct 29, 2026
Agent Detection
Detect whether website visitors are AI agents or people, with a dashboard of visitors and sessions.
New
Resemble Detect
Oct 28, 2026
Custom Investigators via API with structured output
Run your team's custom Investigators through the API and have them return results in a catalog agent's layout.
New
Resemble Detect
Oct 27, 2026
Single Deepfake Visualization section in image reports
Image reports now show the label, score and heatmap together in one section.
+
Improved
Resemble Detect
Oct 23, 2026
Image attack types and document forgery detection
Image detection now reports attack types, covers manual edits and document forgeries, and localizes edits more precisely.
+
Improved
Resemble Detect
Oct 22, 2026
Send the calendar consent link to your IT admin
Team admins who are not Microsoft admins can send the org calendar consent link to IT for approval.
New
Resemble Meetings
Oct 22, 2026
Enforced SAML SSO
Enterprises can require SAML SSO for their users and email domains.
New
Oct 21, 2026
Live Signal, Identity and Intelligence on the meeting bot
The meeting bot now runs Signal, Identity and Intelligence live, with in-call chat alerts and a post-call report email.
Changed
Oct 19, 2026
Teams video quality controls and rescans
Native Teams organizations can rescan participants manually or on a schedule and control video quality.
New
Resemble Meetings
Oct 15, 2026
Signal custom categories run independently
Custom Signal categories are now evaluated on every item, and fraud detection can be turned off per team.
+
Improved
Oct 14, 2026
Video attack-type classification
Fake video results now say how the fake was most likely made, shown in the API and the Detect report.
New
Resemble Detect
Oct 13, 2026
Change auto-join while connected
Auto-join preferences can now be changed after a calendar is connected, and new calendars default to all meetings with a link.
+
Improved
Resemble Meetings
Oct 12, 2026
Report incorrect verdicts from the Teams panel
Flag a wrong audio or video verdict directly from the native Teams side panel.
New
Resemble Meetings
Oct 10, 2026
Signal v2
Signal v2 is the new default Signal engine in the app, with Signal v1 still available through the API.
New
Oct 8, 2026
AI music detection API
Detect AI-generated music with the new /api/v2/detect/music endpoint, available to all Detect users.
New
Resemble Detect
Oct 6, 2026
Sign in with Resemble (OAuth 2.0 and OpenID Connect)
Resemble is now an identity provider, so other apps can offer Sign in with Resemble.
New
Sep 28, 2026
Voice Design removed
Voice Design is no longer available.
Removed
Sep 28, 2026
Larger watermarking uploads in original format
Watermarking now accepts files up to 200 MB and returns them in their original format.
+
Improved
Resemble Watermarker
Sep 26, 2026
Choose native Teams or meeting bot during onboarding
Organizations pick between native Microsoft Teams protection and a meeting bot when onboarding.
New
Resemble Meetings
Sep 26, 2026
Signal, Intelligence and Identity in native Teams
The native Teams side panel now runs Signal, Intelligence and Identity alongside deepfake detection (Detect)
New
Resemble Meetings
Sep 15, 2026
Post-call stakeholder email for native Teams
Native Microsoft Teams protection now sends a post-call summary email to stakeholders.
New
Resemble Meetings
Sep 4, 2026
Organization-owned meetings for org calendars
Org calendar meetings now belong to the organization, with admins seeing every meeting.
Changed
Resemble Meetings
Sep 1, 2026
Long-form text detection uses the latest model
Text AI detection now routes long-form text to the current text model.
+
Improved
Resemble Detect
Sep 1, 2026
Video DFD model update: 2.3x better heatmap localization
New video detection with sharper heatmaps and a lower error rate.
+
Improved
Resemble Detect
Sep 1, 2026
SynthID for audio and video, and watermark checks in Detect
SynthID detection now covers audio and video, and Detect can optionally check for watermarks.
New
Resemble Watermarker
Aug 12, 2026
Billing API access with API tokens
Manage your subscription through the API using your regular bearer token.
New
Aug 10, 2026
Detect feedback on reports and via API
Grade a Detect verdict and tell us what it should have been, from the report page or the API.
New
Resemble Detect
Aug 7, 2026
Image DFD model update: improved performance
New image detection release with a lower error rate on the same evaluation set.
+
Improved
Resemble Detect
Aug 5, 2026
Clearer HTTP errors for synchronous Detect requests
Synchronous /api/v2/detect requests now return proper HTTP error codes when analysis fails.
+
Improved
Resemble Detect
Aug 3, 2026
Video DFD model update: calibrated scores, 4x faster
New video detection release with calibrated scores and four times faster analysis.
+
Improved
Resemble Detect
Jul 30, 2026
Intelligence preflight check in Detect reports
Running Intelligence from a Detect report now checks the media first.
+
Improved
Resemble Intelligence
Jul 24, 2026
Detect callbacks include the Intelligence report
When Intelligence is enabled, the Detect callback now waits for Intelligence to finish and includes its report.
Changed
Resemble Intelligence
Resemble Detect
Jul 23, 2026
PerTh and PerTh Multimodal watermark decoding
Watermark detection now recognizes both PerTh and PerTh multimodal watermarks and reports which version was found.
+
Improved
Resemble Watermarker
Jul 22, 2026
Auto-join options when connecting a calendar
Users choose which meetings the Meetings bot joins as part of connecting their calendar.
+
Improved
Resemble Meetings
Jul 22, 2026
Legacy voice versions ended for marketplace voices
Marketplace voices no longer run on legacy voice templates; they remain available on the Ultra voice version.
Removed
Jul 22, 2026
Drag and drop anywhere to start a Detect report
Drop an audio, video, image or ZIP file anywhere on the Detect page to start a new report.
+
Improved
Resemble Detect
Jul 17, 2026
Face-only mode for video detection
The video deepfake detector now supports a face-only analysis mode.
New
Resemble Detect
Jul 13, 2026
Unified Identity API
The audio-only and multimodal identity endpoints are now a single API at /api/v2/identity.
Changed
Resemble Identity
Jul 7, 2026
Meeting Intelligence toggle for personal and org calendars
Intelligence analysis in Meetings can now be switched on per calendar, including personal calendars.
New
Resemble Meetings
Resemble Intelligence
Jun 30, 2026
Default to rapid voice type for API-created voices
Voices created via the API now default to the rapid voice clone type.
Changed
Resemble Voice
Jun 29, 2026
Upgraded voice flow and deprecation of legacy voices
Streamlined the voice creation flow and began deprecating all older voice models in favor of the current generation.
Changed
Resemble Voice
Jun 24, 2026
C2PA detection fallback in Detect
Detect now falls back to reading C2PA content credentials when present to support provenance-based verification.
New
Resemble Detect
Resemble Watermarker
Jun 24, 2026
Speech-to-Text upgraded to Gemini 3.5
Upgraded the Speech-to-Text backend to Gemini 3.5 for better transcription accuracy.
+
Improved
Resemble Voice
Jun 22, 2026
Watermarking report
Added a dedicated report view summarizing watermark embedding and detection results.
New
Resemble Watermarker
Jun 22, 2026
Implicit and explicit watermarks
Watermarking now supports both implicit (invisible) and explicit (custom message) marks.
New
Resemble Watermarker
Jun 22, 2026
Audio DFD model update: 4% EER
New audio deepfake detection model deployed: equal error rate down to 4%, with higher precision, recall, and VoIP robustness.
+
Improved
Resemble Detect
Jun 18, 2026
Simulations and Agents removed from the sidebar
Removed the Simulations and Agents entries from the left sidebar to streamline navigation.
Removed
Resemble Voice
Jun 18, 2026
Guard rebranded to Trace
The Guard product was renamed to Trace across the frontend, bundling Signal and Watermarking.
Changed
Resemble Intelligence
Resemble Watermarker
Jun 18, 2026
"Unlock Voice Clones" upgrade banner removed
Removed the persistent "Unlock Voice Clones" upgrade banner from the app.
Removed
Resemble Voice
Jun 15, 2026
C2PA signing and SynthID detection
Added C2PA signing of outputs and SynthID detection to the watermarking stack.
New
Resemble Watermarker
Jun 10, 2026
Voice Design moved to Dramabox model
Migrated Voice Design generation from Dreamvoice to the new Dramabox model.
Changed
Resemble Voice
Jun 9, 2026
Intelligence model updated to Gemini 3.5 Flash
Swapped the Intelligence expert model from Gemini 3.1 Pro to Gemini 3.5 Flash.
Changed
Resemble Intelligence
Jun 9, 2026
Intelligence Playground
A dedicated playground for running and iterating on Intelligence analyses directly in the app.
New
Resemble Intelligence
Jun 4, 2026
Native Microsoft Teams integration for Meetings
Meetings now integrates natively into Microsoft Teams, with no bot joining the call and admins able to roll it out silently across the org.
New
Resemble Meetings
Jun 3, 2026
Person vs. brand identities with Face Match API
Identity now distinguishes person and brand identity types and supports face matching via a Face Match API.
New
Resemble Identity
Jun 1, 2026
Audio watermarking migrated to PerTH V2
Moved audio watermarking to the PerTH V2 engine on Cerebrium for stronger, more robust marks.
+
Improved
Resemble Watermarker
May 20, 2026
Deepfake report print includes video thumbnail and heatmap
Printed and exported deepfake reports now include a video thumbnail and the analysis heatmap.
+
Improved
Resemble Detect
May 18, 2026
C2PA content credentials in watermark detection
Watermark detection now reads C2PA content credentials, with Resemble as an approved C2PA issuer.
New
Resemble Watermarker
May 13, 2026
Resemble Labs in the sidebar
A new Labs section surfaces models published under the research banner.
New
Resemble Intelligence
May 13, 2026
Multimodal Watermarking UI
A new UI for applying and detecting watermarks across audio, image, and video.
New
Resemble Watermarker
May 8, 2026
Voice cloning pricing: first clone free, then $2 each
Updated voice cloning so the first clone is free and each additional clone is $2, with card capture deferred until after the first clone.
Changed
Resemble Voice
May 6, 2026
Intelligence analysis inside Meetings
Meetings now uploads each participant's stream to Intelligence post-call and shows the analysis.
New
Resemble Meetings
Resemble Intelligence
May 5, 2026
AMR and 3GP media support
Added support for AMR and 3GP audio formats across upload and processing.
+
Improved
Resemble Voice
May 4, 2026
Fine-tuning removed from sidebar navigation
Removed the legacy Fine-tuning entry from the left sidebar.
Removed
Resemble Voice
Apr 30, 2026
Fraud, Liveness, and Digital Alteration analysis in Intelligence
Intelligence reports now include Fraud Analysis, Liveness Detection, and Digital Alteration experts, all powered by Gemini.
New
Resemble Intelligence
Apr 29, 2026
Resemble Ultra (powered by xAI) is live
New xAI-powered Ultra voice model now live in the portal, with six new default voices and $2 voice cloning (first clone free).
New
Resemble Voice
Apr 28, 2026
Detect UI revamp
Rebuilt the Detect experience with a cleaner report layout and updated playground.
+
Improved
Resemble Detect
Apr 27, 2026
Voice Design default TTS set to Gemini 3.1 Flash TTS preview
Voice Design previews now default to the Gemini 3.1 Flash TTS preview model.
Changed
Resemble Voice
Apr 23, 2026
Resemble Signal
Signal, an API-first intelligence layer on top of the detection stack, is now available to admins.
New
Resemble Intelligence
Resemble Detect
Apr 23, 2026
Detect reports scoped to team members and admins
Detect report links are no longer publicly accessible - access is limited to team members and Resemble admins.
Changed
Resemble Detect
Apr 10, 2026
Right-to-left language support in Speech-to-Text
Added right-to-left (RTL) rendering and handling for transcripts in Speech-to-Text.
+
Improved
Resemble Voice
Apr 5, 2026
Provider-agnostic detection pipeline
Refactored detection jobs to be provider-agnostic with a dedicated inference worker and Replicate polling fallback.
+
Improved
Resemble Detect
Apr 4, 2026
Cloning from dog barks
Voice cloning now supports non-speech source audio, including cloning a character voice from dog barks.
New
Resemble Voice
Mar 19, 2026
Admin Slack notifications for detections
Admins can configure per-team Slack notifications that fire when a team runs a deepfake detection.
New
Resemble Detect
Mar 19, 2026
Zero Retention (Privacy) Mode for Detect
Added a Zero Retention mode so detection media is not persisted after analysis, behind a feature gate.
New
Resemble Detect
Mar 18, 2026
Speech-to-Text file size limits increased
Speech-to-Text now supports files up to 4 hours long and 2GB in size.
+
Improved
Resemble Voice
Mar 17, 2026
Visual DFD model update for non-face content
Image and video detection model update improving robustness on content without faces, including war-related deepfakes.
+
Improved
Resemble Detect
Mar 17, 2026
Text AI Detection API
Added an API endpoint to detect AI-generated text, extending Detect beyond audio, image, and video.
New
Resemble Detect
Mar 16, 2026
LoRA scaling and lower default CFG for cloned voices
Enabled LoRA scaling in production and lowered the default CFG weight for more expressive cloned voices.
+
Improved
Resemble Voice
Mar 13, 2026
Reverse image search in Detect
Detect can now run a reverse image search to add real-world context when assessing whether an image is authentic or AI-generated.
New
Resemble Detect
Mar 13, 2026
Custom Pronunciations (out-of-vocabulary overrides)
Define custom pronunciations per project for out-of-vocabulary words, with automatic cache sync and sub-10ms lookup at synthesis time.
New
Resemble Voice
Mar 10, 2026
Customizable Meetings bot name
Teams can now customize the display name of the Resemble meeting bot.
New
Resemble Meetings
Mar 9, 2026
Organization calendar auto-sync for Meetings
Admins can connect an org calendar so users and meetings auto-sync and bots auto-join based on preferences.
New
Resemble Meetings
Feb 26, 2026
Long-form synthesis coordinator
Added dedicated coordinator jobs and queues to handle long-form text synthesis reliably at scale.
+
Improved
Resemble Voice
Feb 25, 2026
Bulk delete for Detect
Added the ability to delete multiple detections at once.
+
Improved
Resemble Detect
Feb 24, 2026
Resemble Identity in the app
Added the Identity product into the main app experience.
New
Resemble Identity
Feb 18, 2026
Multiple expert models in Intelligence
Intelligence can now run multiple expert models and enable grounding for detect-driven analysis.
+
Improved
Resemble Intelligence
Feb 13, 2026
Cleanvoice AI as the primary audio enhancement provider
Switched the audio enhancement pipeline to use Cleanvoice AI as the primary provider.
Changed
Resemble Voice
Jan 22, 2026
Deepfake voice detection in Meetings
The Meetings integration can now run deepfake voice detection on participant audio streams.
New
Resemble Meetings
Resemble Detect
Jan 20, 2026
HiFi-GAN vocoder update to remove high-pitch artifacts
Updated the HiFi-GAN vocoder to eliminate high-pitch artifacts in synthesized audio.
+
Improved
Resemble Voice
Jan 14, 2026
Detect email notifications
Detect can now send email notifications when a detection completes.
New
Resemble Detect
Jan 13, 2026
Image Intelligence
Extended Intelligence reporting to images, adding analysis on top of image detection.
New
Resemble Intelligence
Resemble Detect
Filter
Clear filter
Resemble Detect
Resemble Identity
Resemble Intelligence
Resemble Meetings
Resemble Voice
Resemble Watermarker
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Clear filter
Apply
Filter