Models
The models behind Sume's video, image, speech, and music endpoints: ids, clip lengths, resolutions, aspect ratios, audio, references, and migration.
Start with What AI models does Sume support? Every model id, by API surface
HeyGen ElevenLabs v3 model_id per request vs Sume TTS
HeyGen's speech endpoint takes settings.model_id such as eleven_v3 per request. Sume TTS 1.0 hides model ids; its separate TTS Router lists models explicitly.
Tavus Phoenix-4.5: photo rules vs a Sume photo avatar
Tavus Phoenix-4.5 starts a face from a photo in minutes and allows glasses, jewelry and hair. Sume creates an avatar from a public HTTPS image URL.
OmniHuman 1.5 API: native 1080p vs Sume avatar 720p
BytePlus says OmniHuman 1.5 outputs native 1080p from one image plus audio. Sume's Avatar Video currently outputs 720p; its video models list 1080p separately.
Mirage Avatar X: a 10-second AI twin vs Sume avatar inputs
Captions' Mirage Avatar X powers its avatars and AI twins, and a twin needs ten seconds of footage. Sume avatars come from a prompt, a profile or an image.
HeyGen photo avatar hand gestures vs Sume Motion Control
HeyGen's motion_prompt still needs an animation reference for Avatar V photo avatars. On Sume, body motion is a separate Motion Control route, not a prompt.
GPT Image 2 supported aspect ratios on Sume: 5:4, 9:8, 4:5
On Sume, gpt-image-2 accepts 5:4, 9:8 and 4:5 on top of the common ratios, plus custom pixels with a 3:1 limit. The exact list and the 9:8 size to send.
Generative Extend any aspect ratio: Sume video ratios
Premiere's Generative Extend now takes any aspect ratio. Sume's gemini-omni-flash-1.1 makes 16:9 or 9:16 clips; for other shapes, conform with Timeline fit.
Voice cloning API: clone once in the app, speak via the API
Sume has no API route that creates a voice clone. You clone once in the app, then send the voi_ id to the text to speech API on every call.
How to colorize a black and white video with AI
Colorize a black and white video with an AI video-to-video edit: send the clip and a prompt naming the colors. The model invents them.
AI outfit change video: change clothes in a clip with AI
Change someone's outfit in an existing video with an AI video-to-video edit: name the garment, what it becomes, and what must stay the same.
Batch edit photos with AI: one edit across many photos
To batch edit photos with AI, send the same edit prompt once per photo, with that photo as the reference. How to script it, pace it, and what it costs.
AI sky replacement: swap the sky and keep the photo
AI sky replacement: send the photo to an image-edit model, describe only the new sky, and list what stays. Then check roof and tree edges. Cost and limits.
Remove shadow from photo with AI: edit it or cut it out
To remove a shadow from a photo with AI, send the photo to an image-edit model, name the one shadow to remove, and list what stays. Prompts, cost, limits.
Kling 2.6 vs 3.0: length, resolution, audio and price
Kling 3.0 makes 3–15 s clips up to 4K with audio and multi-shot; 2.6 makes 5 or 10 s shots at 720p or 1080p. Kling's own specs and prices, dated.
AI avatar video aspect ratio: square, 3:4 and vertical 9:16
Sume's avatar video endpoint takes aspect_ratio 1:1, 3:4, 9:16, 4:3 or 16:9, defaulting to 9:16, at 720p. Which value to send for square or vertical.
AI image negative prompt: what to do when the API has no field
Sume's image API has no negative prompt field. Describe what you want instead, edit with a mask, and keep references. The fields that do exist.
AI image generator with readable text: which Sume models to try
Which Sume image models have a vendor claim about text in images, what each vendor says, and the quality setting Sume's docs suggest for dense text.
Does Lyria 3.5 music carry a SynthID watermark?
Google says all Lyria 3.5 audio includes a SynthID watermark. What that means for tracks made through an API, and what Sume's docs do and do not say.
AI video multiple faces consistency: Luma's 8-face limit, Sume's caps
Luma Ray3.2 lists facial performance tracking for up to 8 faces. Sume has no such setting; the limit is how many reference images each video model accepts.
Why AI video models do not lip sync to a voiceover, and what to use
Sume docs: video models do not lip-sync to generated speech or a voice-over. For a talking face use Avatar video or the lip-sync endpoint (still plus audio).
Cartesia Sonic 3.6 API: which model id to send
Send sonic-3.6 for the latest stable Sonic 3.6, a dated id to freeze it, or sonic-preview for beta. Which of these ids Sume's TTS Router lists.
ChatGPT Images 2.5 vs GPT-Image-2.5: which name is the API?
ChatGPT Images 2.5 is OpenAI's product; GPT-Image-2.5 Flare and Sunburst are the API models. How the names map to Sume ids and which features stay in ChatGPT.
Does ChatGPT Images 2.5 add a watermark? C2PA explained
OpenAI says ChatGPT Images 2.5 uses C2PA metadata and invisible watermarking to identify its images. What that means for files you get through an API.
Claude Sonnet 5.5 or Opus 5.5 for an agent that calls a video tool?
Sonnet 5.5 and Opus 5.5 differ in price and release date on Anthropic's pages. Which facts matter when the tool is Sume's video generation, and what stays same?
Text to speech Korean API: 90+ languages claim vs what Sume lists
Eleven v4 says 90+ languages. Sume's TTS schema publishes no language count, only a language field and five Sonic ids. Request Korean or Japanese and test it.
Eleven v4 audio tags [laughs]: how to use them, and Sume's controls
Eleven v4 reads inline tags such as [laughs] and [light rain] in the text. Sume's TTS schema has no tag syntax; it has speed, volume and emotion controls.
ElevenLabs Eleven v4 API: what it is and how to reach it
Eleven v4 and v4 Turbo launched September 28, 2026 on ElevenLabs' own API. What ElevenLabs says they do, and which TTS ids Sume's router lists.
FLUX.2 dev commercial use: what the model card says
FLUX.2 [dev] weights carry the FLUX non-commercial license, yet the card says outputs can be used commercially as that license describes. The exact wording.
FLUX.2 flex text rendering: prompt tips and the Sume model id
Black Forest Labs positions FLUX.2 [flex] for text and fine detail. How its typography guidance reads, and how to call black-forest-labs/flux.2-flex on Sume.
FLUX.2 hex color prompt: how to write it, with an API call
Black Forest Labs says FLUX.2 matches hex codes in prompts. The syntax it documents, the limits it admits, and a flux.2-pro call on Sume.
FLUX.2 pro vs Nano Banana Pro API: request specs side by side
Request parameters that differ between black-forest-labs/flux.2-pro and google/nano-banana-pro on Sume: resolution tiers, aspect ratios, references and price.
FLUX.2 prompt guide: structure, length and no negatives
Black Forest Labs' FLUX.2 prompt rules: subject, action, style, context; 30-80 words; no negative prompts. Which apply to flux.2-pro on Sume.
FLUX 3 vs FLUX 2: which one you can call on Sume today
FLUX 3 vs FLUX 2 for image work: BFL's notes start FLUX 3 with video, and Sume's image catalog serves FLUX.2 Pro and Flex. What that means for stills.
FLUX 3 video 20-second clips: what Sume's video API offers
FLUX 3 Video makes up to 20 s clips at 1920x1088. Sume does not list it, but seedance-2.5 and wan-3.0 accept 20 s requests. Durations by model.
Gap or click when joining audio files: use wav, not mp3
Sume's Timeline audio joins up to 20 Sume-hosted parts with no silence at the seams. Its docs say to keep wav, because mp3 adds padding at every edge.
Gemini Live Avatar vs a video avatar API: live or rendered?
Gemini 3.8 Live Avatar streams a lip-synced face in a conversation. Sume's avatar video renders a finished clip from a script. Which job needs which.
Gemini Live Avatar: 97 languages and SynthID, explained
Google says Gemini 3.8 Live Avatar covers 97 languages and adds SynthID to audio and video. What each claim covers, and what it says about other avatar tools.
Gemini Omni 1.1 Flash 360p drafts: what a cheap preview costs
Gemini Omni Flash 1.1 can render 360p previews. On Sume a 360p second is billed at 30% of a 720p second, so drafts cost less than finals.
Gemini Omni Flash 4K: clip length, upscaling and price
Gemini Omni Flash 1.1 renders 4K clips of 3 to 10 seconds on Sume, and Google labels its 4K output upscaled. Length versus Veo 3.1, plus cost.
Gemini Omni Flash prompt guide: one shot, audio, text
Google's Omni Flash prompt tips: ask for a single continuous shot, put negatives in the prompt, describe the audio, spell out on-screen text. Plus a Sume call.
Gemini Omni Flash vs Veo 3.1: which does Google recommend when
Google's video page names Gemini Omni Flash the default, Veo 3.1 for scene extension, last-frame control or legacy pipelines. Facts side by side, plus Sume ids.
Gemini Omni prompt timecodes: [0-3s] and scene cuts
Gemini Omni Flash takes timing in plain words or a [0-3s] timecode syntax, so you can script cuts inside one clip. Google's examples and a 10-second Sume call.
Gemini Omni video edit prompts that keep everything else the same
Google says short prompts work best when you edit a video with Gemini Omni Flash, and to add Keep everything else the same. Examples, limits and a Sume call.
Gemini Omni reference video: is the audio used? No
Gemini Omni Flash accepts video references but not audio: Google says audio in a reference clip is ignored. Limits, Sume's fields, and models that take audio.
Does Gemini Omni video have a SynthID watermark?
Google says all Gemini Omni Flash videos include an invisible SynthID watermark. What that means for API clips, YouTube disclosure, and what Sume's docs say.
Google Flow video length: 4 to 10 seconds by model
Google Flow makes 4, 6 and 8 second clips with Veo 3.1 and 4 to 10 seconds with Gemini Omni Flash 1.1. Length by model and mode, from Google's help page.
Does Sume Auto use GPT Image 2.5? What sume/auto picks for images
Sume's docs say Auto image routing continues to use Flare, GPT Image 2.5. Sume never says which family ran on a call, so pin openai/gpt-image-2.5 if it matters.
GPT Image 2.5 Flare vs Sunburst: what each model page says
OpenAI calls Flare its model for everyday image generation and Sunburst its most capable for generation and editing. What each page lists, and both ids on Sume.