Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
How to use Sume 2.0
Sume 2.0 in the app itself: how you get into Sume, Chat and Studio from the first window, and what to press in each, one scenario at a time.
AI video API clip length: which Sume models accept it, and the cost
Which Sume video models accept a clip length by API, which refuse it at validation, and what each accepting model costs, one row per clip length.
One AI video job up to 30 seconds: Wan 3.0 vs Seedance 2.5 cost
Only Wan 3.0 and Seedance 2.5 on Sume take more than 15 seconds in one request. What one clip costs on each at every resolution, by clip length.
AI video longer than 30 seconds on Sume: how many jobs, and the cost
No Sume video model makes more than 30 seconds in one job. How longer videos split into jobs on Wan 3.0 or Seedance 2.5, and what the set costs, by length.
Gemini Omni Flash 1.1 clip cost on Sume, by length and resolution
What Gemini Omni Flash 1.1 costs on Sume per clip and per set of clips, from 360p to 4K, for each length it accepts. Native synced audio is included.
Voiceover plus captions on Sume: cost by script length
Voicing a script and captioning the result is two charges on Sume: text-to-speech by length and one caption job. The total for every script length priced.
Wan 3.0 cost for sets of short ad clips on Sume, vs Omni Flash
What a set of short ad clips costs on Sume with Wan 3.0 at 480p, 720p and 1080p, next to Gemini Omni Flash 1.1, for every set and length these posts priced.
H3 Max Recast person swap cost on Sume, by source video length
H3 Max Recast swaps the people in a video for people from photos. What it costs on Sume at 768p and 1080p for each source video length these posts priced.
Seedance 2.5 product ad cost on Sume, by number of ads
What a run of 10-second product ads costs on Sume with Seedance 2.5 at 720p and 9:16: one ad's price times the count, for every count these posts priced.
Text-to-speech cost on Sume, by script length
Sume TTS is priced per character, spaces and punctuation included, and a long script splits into several jobs. The cost of scripts from a tutorial to a book.
Seedance 2 vs 2.5 on Sume: clip cost by length and resolution
What a Seedance 2 and a Seedance 2.5 clip cost on Sume at 480p, 720p and 1080p in 9:16, for each clip length these posts priced, side by side.
Sume Avatar 1.0 creation cost: the price per avatar
Creating an Avatar 1.0 avatar on Sume is a fixed price per avatar, so a batch costs that price times the count. The total for every batch size priced.
Caption videos with an API: the cost on Sume per caption job
Captioning on Sume is a fixed price per caption job for videos up to the documented length, so a batch costs that price times the number of videos.
MiniMax H3 vs H3 Max on Sume: clip price by length, 480p and 768p
What MiniMax H3 and the faster H3 Max variant cost on Sume at 480p and 768p, for each clip length these posts priced, side by side.
GPT Image 2.5 cost on Sume by quality, size and image count
What GPT Image 2.5 images cost on Sume at each quality tier, square and 16:9, for every image count these posts priced. One image per request.
Sume avatar talking video cost by length and quality tier
What an Avatar 1.0 talking video costs on Sume at the standard, plus and max tiers, with and without a product image, for each length and count priced.
AI music tracks on Sume Music 1.0: the cost per generation
Sume Music 1.0 charges a fixed price for each accepted generation, whatever the prompt, so a set of tracks costs that price times the count.
Kling 3 clip cost on Sume with generated audio on or off
What Kling 3 clips cost on Sume with and without generated audio, by clip length and count. Audio adds the provider's per-second surcharge.
Sume Timeline render cost by video length
The Timeline tool bills per output minute, rounded up, so the render cost of a video follows its length. The cost for every length these posts priced.
Transcription cost on Sume STT, by audio length
Sume STT 1.0 bills per audio minute, so a transcript costs that rate times the minutes. The cost of interviews, webinars, workshops and stream replays.
Background removal cost on Sume, per product photo
Remove background (RMBG 1.0) on Sume is a fixed price per image, whatever its size, so cutting out a batch costs that price times the photo count.
Video upscale cost on Sume, by footage length
Video Upscale 1.0 on Sume bills per second of footage, so upscaling costs that rate times the length, from a short clip to hours of footage.
Image upscale cost on Sume: the price per image
Image Upscale 1.0 on Sume reserves a fixed amount per image, so upscaling a batch costs up to that amount times the image count.
AI video clip price on Sume, by model, length and resolution
The price of one AI video clip on every Sume video model, by clip length and resolution, as each of these posts read the catalog.
Transcript cost for podcasts and calls: MAI-Transcribe vs Sume STT
What transcribing podcasts, calls, ads and back catalogs costs on Microsoft's MAI-Transcribe-2-Streaming and on Sume STT 1.0, for each job priced.
Cheapest AI video model on Sume by clip length and resolution
Which Sume video model makes a clip of a given length and resolution for the least, and what the dearest model that can make it costs.
Veo 3.1 at Google's list price vs the cheapest Sume row
Google's list price for a Veo 3.1, Veo 3.1 Fast or Veo 3.1 Lite clip next to the cheapest Sume row that makes the same length and resolution. Price only.
Sume TTS vs ElevenLabs: narration cost by character count
Sume TTS against ElevenLabs Flash, Turbo and multilingual models for the same number of characters, from IVR prompts to a full library.
Sume STT vs ElevenLabs Scribe v2: transcript cost by hours
What transcribing hours of calls or recordings costs on Sume STT and on ElevenLabs Scribe v2. On cost alone, Scribe v2 is cheaper for plain transcripts.
Sume Music vs ElevenLabs Music: cost by track count and length
Sume charges a fixed price per generation; ElevenLabs charges per minute of music. Which is cheaper depends on track length, for every set priced.
Spokesperson ad cost on Sume: avatar video plus stills and b-roll
What a short spokesperson ad costs on Sume when it combines an avatar video with GPT Image 2.5 stills and b-roll clips. The avatar video is most of it.
What an AI video budget buys on Sume: seconds and length by model
How many seconds of video a budget buys on each Sume model, and the longest clip each model makes under a per-clip price ceiling, at 720p and 1080p.
Nano Banana 2.1 image cost on Sume, by resolution tier and count
What a set of Nano Banana 2.1 images costs on Sume at the 0.5K, 1K, 2K and 4K tiers: the per-image price times the count, for every set these posts priced.
Ideogram 4.5 image cost on Sume at low, medium and high quality
What a set of Ideogram 4.5 images costs on Sume at low, medium and high quality, for every set these posts priced. Image size does not change the price.
Grok Imagine Video 1.5 Lite vs Sume: clip cost by length
xAI's direct per-second price for Grok Imagine Video 1.5 Lite next to Sume's grok-imagine-video-1.5 at 480p and 720p, for one clip and a hundred, by length.
Vidu Q4 Preview vs Sume: clip cost by length and resolution
Vidu Q4 Preview's launch starting rate per second next to the Sume model priced for the same clip, for one clip and for a dozen, at 480p, 720p and 1080p.
MAI-Voice-2.1 vs Sume TTS: narration cost by character count
Microsoft's per-million-character list price for MAI-Voice-2.1 and MAI-Voice-2.1-Flash next to Sume TTS 1.0 jobs, for every narration length priced.
Sora API is gone: a replacement clip on Sume, priced by model
OpenAI removed the Videos API and the Sora 2 models, with no replacement. What a replacement clip costs on each Sume video model, by length and resolution.
Verify a Sume webhook signature in Fastify, Django and Flask
Each framework hands you the request body differently. Verify the Sume signature over the exact raw body, then parse it, in Fastify, Django and Flask.
ACE-Step on Sume: 240 s max, billed per second not per minute
ACE-Step is the Music Router id ace-step: 5–240 s via duration_seconds, billed per second of audio, so a 45 s clip costs less than a 60 s one.
CassetteAI Music on Sume: a 90 s track bills 2 minutes
CassetteAI Music runs on Sume's Music Router as cassetteai-music: 10–180 s via duration_seconds, billed per started minute, so 90 s costs two minutes.
ElevenLabs Music v2.5 on Sume: 300 s max, started-minute billing
ElevenLabs Music v2.5 is the Music Router id elevenlabs-music-2.5: 10–300 s via duration_seconds, billed per started minute, so 61 s costs two minutes.
Music Router duration_seconds: 4 models take it, 5 do not
Since Oct 14, 2026 four Sume Music Router models accept duration_seconds (5–300 s ranges); five still set length from the prompt and reject the field.
Lyria 2 on Sume: one 30 s instrumental clip, no length field
Lyria 2 on Sume's Music Router writes one 30-second instrumental clip per call and refuses duration_seconds; stitch clips or pick another engine.
MiniMax Music 2.6 on Sume: vocals from a 10-2,000 character prompt
MiniMax Music 2.6 on Sume's Music Router writes lyrics from your 10 to 2,000 character prompt, takes no duration_seconds and bills a flat price per track.
Stable Audio 2.5 on Sume: a 190 s track costs the same as a 5 s one
Stable Audio 2.5 on Sume's Music Router takes duration_seconds 5 to 190 and bills one flat price per track, so ask for the full length you need.
HelixWorld makes 121 frames at 24 FPS: Sume rows that run longer
HelixWorld's preview caps a run at 121 frames, about 5 seconds at 24 FPS. Sume's video rows with sound run 5 to 15 seconds; here is the arithmetic and the rows.
Is HelixWorld on Sume? No: a preview checkpoint, no hosted API
HelixWorld, Noiz AI's interactive video-and-stereo-audio model, ships as weights and a browser demo. Sume lists no id for it; these rows return sound.