Descript is an AI-powered video and audio editor that lets you cut recordings by editing their transcript, then clean up, caption, translate and repurpose the result. Underlord, its AI co-editor, plus Studio Sound, voice cloning and screen recording turn a single tool into a full production pipeline for creators and teams.
Tellers is an AI video editing workspace where conversational agents cut, score, caption and finish videos from a script, a brief or your own footage — and every edit stays editable in a timeline you control.
Descript is an AI-powered video and audio editor that lets you cut recordings by editing their transcript, then clean up, caption, translate and repurpose the result. Underlord, its AI co-editor, plus Studio Sound, voice cloning and screen recording turn a single tool into a full production pipeline for creators and teams.
Text-based editing
Edit audio and video by deleting, rearranging or retyping words in the automatic transcript, with a full multitrack timeline available when you need it.
Underlord AI co-editor
Describe the edit you want in plain language and let the AI assistant assemble a tight cut, add clips and handle repetitive production work.
Studio Sound and speech regeneration
Remove background noise, level out voices, and fix misread lines with Regenerate Speech using a clone of your own voice.
Captions, translation and clip export
Generate subtitles and transcripts in a click, translate video into other languages, and reformat long recordings into shareable vertical clips.
優勢與優點
+Editing video by editing a transcript is dramatically faster than timeline scrubbing for interview, podcast and talking-head content
+Audio and visual AI features (Studio Sound, Eye Contact, Green Screen, Regenerate Speech) cover fixes that would otherwise need several tools
Recording, editing, captioning, translation and clip export all live in one workspace, reducing handoffs
+Remote Rooms recording and link-based review with time-coded comments suit distributed teams
+Strong enterprise story: SOC 2 Type II, SAML SSO, SCIM and GDPR-compliant data handling
限制
–Heavy AI features and exports are gated behind paid plans, and free-tier limits are tight
–Long or complex projects with many tracks can feel heavier and slower than a dedicated non-linear editor
–Best results still come from clean source audio, so noisy recordings may need manual attention
–Advanced users who need granular effects and color work may still finish in another editor
–Billing is per seat, so costs add up quickly for large teams
Tellers
Tellers is an AI video editing workspace where conversational agents cut, score, caption and finish videos from a script, a brief or your own footage — and every edit stays editable in a timeline you control.
Editing agents that plan the whole cut
Describe the video you want and an agent decomposes the job — cut detection, beat matching, shot selection, captions, audio — then renders a first cut you can keep refining with prompts.
Output stays on an editable timeline
Generated shots, voice, music and captions all land as timeline layers, so nothing is flattened. Editors retain full manual control over every cut and can export an editable project.
Many leading AI models under one subscription
Generate video, images, voice-over, music and sound effects with models such as Google Veo, OpenAI Sora and GPT Image, Runway, Lightricks LTX, Alibaba Wan, ByteDance Seedance and ElevenLabs — paid from a single token pool instead of separate plans.
Script, footage and audio in, finished video out
Start from a written brief, upload raw footage, or bring existing audio such as a podcast or voice take, and let Tellers assemble the visual narrative around it.
優勢與優點
+Editing is conversational but never destructive — the timeline stays editable
+Access to a large roster of third-party generative models inside one subscription and token pool
+Handles the full chain from script or raw footage through captions, voice and music to a rendered cut
+Automation surfaces (agents, skills, MCP, API) make it usable in larger production pipelines
+Strong starting points for common formats like talking heads, lyric videos, launches and real estate
限制
–Token- and storage-based plans mean heavy generative use can raise costs, and full plan details live behind the app rather than on a static price page
–Output quality still depends on the third-party models chosen for each shot, so results vary between job types
–It complements rather than fully replaces a professional NLE for advanced colour, mixing and finishing work
