Simon Says was built for a specific problem in professional video post-production: the gap between having footage and having a working transcript that an editor can actually use inside their NLE. Most transcription tools generate a text file. Simon Says generates a frame-accurate, timecoded transcript that can be imported back into Premiere Pro, Final Cut Pro, DaVinci Resolve, or Avid Media Composer as captions, markers, or sequence data — without leaving the editing application.

That NLE integration depth is what most clearly separates Simon Says from general-purpose transcription tools. An editor working in Final Cut Pro can select an event with dozens of clips, send them to Simon Says through the extension, receive transcripts, and import them as caption tracks and range markers directly on the FCPX timeline. The roundtrip from editorial to transcript and back to editorial, without leaving the application, is Simon Says' defining operational advantage for video professionals. 

What Is Simon Says Best Used For?

Simon Says covers four workflows that video production teams use it for: transcription for dailies logging and interview selects, caption and subtitle generation for deliverable compliance, translation for international versioning, and rough cut assembly from transcript selections in its Assembly mode.

For dailies logging and documentary work, Simon Says' ability to generate frame-accurate transcripts from multiple files simultaneously, with speaker identification and timecode alignment, reduces the logging labour that is otherwise one of the most time-intensive stages of post-production prep. A 10-hour shooting day that would take multiple days to log manually can be transcribed in minutes, giving editors and producers searchable text they can use to identify selects and plan the edit structure before cutting begins.

Subtitle and caption generation is the most volume-intensive workflow Simon Says serves. Editors working on content that requires closed captions, open captions, or SDH subtitles, for broadcast delivery, streaming platform compliance, accessibility requirements, or international distribution, can generate compliant SRT, WebVTT, or platform-specific subtitle files from their transcripts. The Visual Subtitle Editor allows adjustment of timing, character-per-line formatting, and layout without requiring a separate captioning application.

Translation extends the subtitle workflow to international versioning: transcribe in the source language, translate to one or more target languages, and deliver localised subtitle files for each. Simon Says supports over 100 languages for transcription and translation (Simon Says AI). The on-premise version provides the same capabilities for facilities with security requirements that preclude sending media to the cloud.

Simon Says Pricing Overview & Cost Considerations

Simon Says uses a credit-based model where cost is calculated by the duration of audio and video processed, rounded to the minute. Both pay-as-you-go and subscription plans are available. Subscription plans include credit at a substantially reduced per-minute rate compared to pay-as-you-go. Pricing confirmed on Simon Says' pricing and help pages (Simon Says pricing).

• Pay-as-you-go: approximately $0.25/minute ($15/hour). No monthly commitment. Credit is purchased as needed. 

• Subscription plans: reduce the per-minute cost substantially and include credit with the monthly fee. Subscription credit rolls over for up to three periods if unused. Specific subscription tier pricing (starting at $15/month) is confirmed on the Simon Says pricing page (Simon Says pricing).

• Translation and burn-in subtitles are charged separately from transcription, at the same per-minute credit rate. Export to NLE formats and subtitle files is free; credit is only consumed by transcription, translation, and burn-in.

• On-premise (Simon Says On-Prem): Runs as a Linux-based virtual machine on the facility's own hardware. Additional hours available in blocks; volume discounts available & rates starting at $2,500 with 100 hours of credit

For a production company transcribing 50 hours of material per month, the subscription model is materially cheaper than pay-as-you-go. For facilities with security requirements, the on-premise option at $2,500 becomes cost-effective relative to cloud subscription over a medium-term horizon for high-volume use.

Simon Says Reviews: Pros, Cons & Reported Challenges

What Practitioners Report

Simon Says has a practitioner base concentrated in documentary filmmaking, broadcast, and commercial post-production. Feedback from Capterra, the Apple App Store, and industry publications reflects consistent themes around NLE integration and workflow speed (Simon Says on Capterra).

Strengths

• NLE integration depth is the most consistently praised capability. Practitioners describe the FCPX roundtrip, specifically the ability to import transcripts, captions, and range markers directly into the Final Cut timeline, as a meaningful workflow acceleration for documentary and interview-based editing (Simon Says on Apple App Store).

• Frame-accurate timecodes are cited as the feature that most clearly differentiates Simon Says from general-purpose transcription tools. The precision matters for editors using transcripts to navigate footage: a timecode that is off by two seconds creates a caption that is out of sync with the speaker (Simon Says AI).

• Cost relative to human transcription is cited frequently, with practitioners describing the service as saving multiple production days per project at a fraction of the cost of professional human transcription. Accuracy for clear speech is described as sufficient to require only proofreading rather than full re-transcription.

• On-premise option for security-sensitive environments is a meaningful differentiator relative to cloud-only competitors. Government, legal, and entertainment studios handling confidential material have a viable path to the same capabilities without cloud data transfer.

Reported Challenges

• Timecode accuracy is the most common technical complaint. Some practitioners describe subtitle timecodes that are slightly off-sync, requiring manual correction — a friction point that partially offsets the time saving from AI transcription (Simon Says on Capterra).

• Credit cost structure: each step (transcription, translation, burn-in) consumes separate credit, which practitioners describe as requiring careful accounting before starting a multi-step workflow (Simon Says on Capterra).

• Interface is described as functional but less polished than some competitors. Some practitioners note that the subtitle editor has fewer formatting options than dedicated captioning applications (Simon Says on Capterra).

• Support response times are cited as slow by some users, with delays in resolving technical issues requiring workarounds.

Where Simon Says Fits in a Post-Production Stack

Simon Says sits at the transcription and captioning stage of the post-production pipeline, between receiving raw footage or an edited cut and the point where the finished caption files are delivered to the client or platform. In a documentary workflow, Simon Says operates at both ends: at the logging stage before the edit begins (transcribing all interview footage to enable transcript-based selects) and at the deliverable stage after the cut is locked (generating SRT and broadcast caption files for the finished programme).

In a broadcast and streaming delivery workflow, Simon Says handles the caption compliance deliverable that most platforms and broadcasters require: closed captions for accessibility compliance, open captions burned into social versions, and translated subtitles for international distribution. The integration with Premiere Pro, DaVinci Resolve, Final Cut Pro, and Avid Media Composer means these deliverables are generated within the editor's existing workflow rather than requiring a separate application.

How Shade Works Alongside Simon Says

Shade operates as the storage and search layer beneath the Simon Says transcription workflow. Interview footage, dailies, and locked cuts all reside on a ShadeFS mounted drive that presents as a local volume on every workstation. Editors send media from their NLE extension to Simon Says for transcription, receive the timestamped transcript back, and the source files stay on Shade throughout — no upload to a separate storage service, no download cycle between the mounted drive and the transcription tool.

Shade's own auto-transcription with speaker identification indexes the full media library simultaneously, making footage searchable by keyword, speaker, and topic within Shade itself (Shade podcast workflow). For teams running Simon Says for NLE-integrated caption delivery and Shade for library-level search and discoverability, the two capabilities address different parts of the same operational problem: Simon Says produces the deliverable caption file; Shade makes the underlying footage findable without it.

Finished caption deliverables and versioned subtitle files require client review before platform submission. Shade's review and approval workflows provide a structured approval cycle for caption-critical deliverables without requiring a separate review platform.

The Ralph case study documents 35% faster project completion and 33% improvement in content reuse across deliveries for Netflix, Apple TV+, and Spotify. For productions generating large volumes of captioned content across multiple platforms, the infrastructure efficiency beneath the transcription workflow directly reduces the delivery overhead that surrounds it.

Related Shade Guides

Teams evaluating transcription tools are often simultaneously evaluating the storage and media management infrastructure that holds the footage being transcribed. Shade's guide to best cloud storage for video production teams covers the shared storage options that underpin multi-artist workflows where large media libraries need to be accessible alongside their transcript metadata. For teams managing the broader library of approved deliverables and production assets, Shade's guide to best DAM for video production teams addresses the organisational layer beneath the transcription workflow. Teams working in specific NLEs alongside Simon Says will find adjacent context in Shade's guide to best NLE software for video production teams.

Who Simon Says Is Best Suited For

Simon Says is best suited for documentary filmmakers and editors logging large volumes of interview footage, post-production facilities producing broadcast and streaming content that requires compliant caption deliverables, and any production team working in Final Cut Pro, Premiere Pro, DaVinci Resolve, or Avid Media Composer who needs transcripts and captions as native timeline elements rather than external files.

Simon Says is not suited for meeting transcription, real-time captioning of live events, or enterprise-scale accuracy-critical transcription with human review requirements. For those use cases, Verbit or a similar enterprise platform is more appropriate.

To see exactly how Simon Says compares to other transcription & AI logging tools, see our guide comparing the best transcription & AI logging tools for video production. 

Frequently Asked Questions

Does Simon Says work with Final Cut Pro, Premiere Pro, and DaVinci Resolve?

Yes. Simon Says provides extensions for Final Cut Pro X, Adobe Premiere Pro, and DaVinci Resolve, as well as Avid Media Composer integration. The extensions allow editors to send clips directly from the NLE timeline for transcription and import the resulting transcripts, captions, and markers back into the timeline without leaving the editing application (Simon Says AI).

What is Simon Says On-Prem?

Simon Says On-Prem is an on-premise version of the Simon Says transcription engine that runs as a Linux-based virtual machine on the facility's own hardware. It provides the same AI transcription capabilities as the cloud service without sending media files to external servers. It is designed for government, legal, entertainment studios, and other facilities with data security or confidentiality requirements. The on-premise version costs $2,500 including 100 hours of transcription; additional hours are available in blocks.

How is Simon Says different from Descript?

Descript is a transcript-driven media editor where the transcript is the editorial interface. Simon Says is a transcription and captioning tool that generates timestamped transcripts and delivers them to the NLE or as caption files. Descript is best for editing by transcript; Simon Says is best for logging footage, generating caption deliverables, and translating subtitles within an existing NLE workflow.

Final Assessment

Simon Says' strength is in the precision and integration of its output, not the accessibility of its interface. Frame-accurate timecodes, NLE extension integrations for every major professional application, and an on-premise option for security-sensitive environments make it the most operationally specific transcription tool available for video post-production teams. The credit-per-step cost model and occasional timecode accuracy issues require attention, but for the workflows it serves, the alternative is manual transcription that is slower by orders of magnitude.

Simon Says transcribes the footage. Shade manages the library it lives in.