Ka whakatū i te whitiāhua AI

Ka āhei te whakamahi hokohoko 575 tauira Kāore he tohu wai Kāore he rēhita e hiahiatia
Tauira:
+ GPT-5, Claude, Gemini
E tuhituhi ana tētahi whakaaro kōrero. Ka tuhituhi te kaiwhakahaere AI i tētahi tuhituhi-maha-wā, ka whakawātea i ia āhua hei tākaro vitio poto, kātahi ka whakawātea i tētahi tapahi ā-whāiti. Ko te tino pai mō ~3-5 ngā wā poto (10-30 sekone katoa). Ko Cogvideox he wātea; he mārama ake te hunga-video engari he roa ake.
2-4 ngā rerenga. Kei roto ko te kākahu, te pūwhiti, me ētahi atu tohutoro tono.
~3-8 min e ai ki te tauwāhi āhua + tauira
Ka tīmata...
Ko tōtou pouaka whakaata pūoro
Kōwhiringa matatau
Whakamutunga
E iti haere ana ngā token. Tikina he token atu
Kei te hiahia i ngā hua pai ake? Ngā tauira whakapaipai (GPT-5, Claude, Gemini) he kounga teitei ake. Tirohia ngā Mahere

❤️ E hiahia ana Free.ai? Whakapāpāho ki ōna hoa!

Rēhita kia whiwhi i tētahi hono tono, ā, kia whiwhi i te 30,000 token mō ia hoa.

E hiahiatia ana ētahi atu? Rēhita utu kore: 30,000 token/rā
Whakawhanaunga i te wātea

E whakamātau ana i tō tātau tono...

Ka huri i tētahi whakaaro ki tētahi pouaka whakaari-maha me te AI wātea. Ka tuhituhi te kaiwhakahaere i tētahi tuhipānui, ka whakawātea e te AI i ia tirohanga, kātahi ka whakawhāiti ki tētahi whakawhāiti whakamutunga.

He pēhea te whakamahi Ka whakatū i te whitiāhua AI

1
Ka tāuru i tōna tāuru

Type i te kupu, tuku i tētahi faila, whakaahua rānei i te mea e hiahiatia ana e koe. Kāore he tatau e hiahiatia ana.

2
Ka whakatū te kōkā

Ka tukatuka tā mātou AI i tō tono i ngā hēkona noa iho, ma te whakamahi i ngā tauira pūtake tuwhera pai rawa.

3
Whakahua me te tiritiri

Whakataki, tārua, tiritiri rānei i tōna hua. Whakatika noa mō te whakamahinga whaiaro, mākete rānei.

Whakamahia tēnei taputapu mā te API

Mahia aunoatia tēnei taputapu mai i tō ake waehere. He pito REST e hototahi ana ki OpenAI, whakamana mā te tohu Bearer, kāore he SDK anō e hiahiatia. He orite ngā utu tokena ki tō te atanga tukutuku.

curl -X POST https://api.free.ai/v1/video/generate/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A cat playing piano", "duration": 4}'

Ka whakatū i te whitiāhua AI FAQ

Type a story idea in plain English. An AI director (Qwen3-30B) writes a multi-scene script, then a video model (CogVideoX or HunyuanVideo) renders each scene as a short clip, and ffmpeg stitches them into one continuous movie. You get a single MP4 of 10-30 seconds covering 2-6 scenes, much closer to a real short film than a one-shot text-to-video clip.

One-shot text-to-video tools (CogVideoX, HunyuanVideo) only handle a single 4-6 second clip, so characters and settings drift between separate generations because each clip has no memory of the others. The Movie Generator chains an LLM director on top of those models, plans a coherent scene-by-scene script, and concatenates the output. Better for stories. /video/generate/ is still better for a single shot.

Free up to your daily token pool (30,000 tokens/day for signed-in users, 6,000 for anonymous). A 3-scene movie at CogVideoX quality costs ~15,500 tokens, so it usually needs purchased credits: $5 buys 200K tokens, enough for ~13 movies. Premium HunyuanVideo doubles per-scene cost in exchange for sharper detail.

Ka haere te CogVideoX ~60-90 sekon i ia tirohanga; Ka haere te HunyuanVideo ~120-180 sekon i ia tirohanga. Ko te whitiāhua 3-whakaahua CogVideoX e whakamutu ana i roto i te 3-5 min; he whitiāhua 5-whakaahua HunyuanVideo i roto i te 12-15 min. E whakaatu ana te pae nekehanga i te āhua o te whakaaturanga.

Partially. The director writes consistent character descriptions into every scene prompt ("a young woman with red hair, wearing a green coat"), which keeps faces and outfits in the same family. But the underlying video models do not have true character memory, so small drifts in face shape and outfit details are still common. For pixel-perfect consistency you would need IP-Adapter conditioning, which is on our roadmap.

He mārō te whitiāhua, he whakahauhau anime/Ghibli, he pūrākau pūrākau, he mārō te āhua, he āhua 3D Pixar, he 35mm rārangi, he pūtaiao-pūtāhua, he pūrākau. Ka whakawātea ia kāhua i te reo āhua-whakahaere o te kaiwhakahaere me te whakataki o te tauira ataata ki taua āhua. Ka tautokona ngā kāhua ā-ringa mā ngā whakarongo API hāngai.

Not in the UI yet. V1 generates the script and renders the scenes in one shot. The /v1/video/movie/script/ endpoint (script-only) is on the roadmap for users who want to iterate on the script before burning render time. For now the scene prompts are surfaced in the result page so you can see what was generated.

10-30 seconds total in V1 (2-6 scenes × 4 seconds each). Longer films would chain proportionally more scenes, which is possible but expensive (30,000 tokens per scene at CogVideoX, 47,000 at HunyuanVideo). For 1-minute+ films we recommend rendering individual scenes at /video/generate/ and editing them yourself in DaVinci or CapCut.

Ko te V1 e puta mai ana i te ataata whakamātautau. Mō te reo, ka whakahaeretia te tuhituhi mā /rohe/tts/ me tētahi reo kōrero me te tāpiri i te rererangi oro i DaVinci / CapCut / iMovie. Mō tētahi rererangi oro, /pūoro/whakahaere/ e whakaputa ana i ngā rererangi oro-kore. Ko te whakawhanaunga oro ā-iwi i te mahere huarahi (e whakawhirinaki ana ki ngā tauira utu pēnei i te Veo, i te whakawhanaunga pūoro-āhua Sora rānei).

Yes, every generation creates a one-shot share link at /share/<token>/ that lasts 7 days for paid users (24h for anonymous). The token is unguessable (22-char URL-safe), and the share page renders the video with optional captioning. Same share UX as the rest of the platform.

Runway Gen-3 ($15/month minimum, single-clip text-to-video, gorgeous output but no story planning), Sora (still invite-only, exceptional quality), Veo (Google, premium API only). They produce sharper individual clips. The Movie Generator is the script+stitch layer on top of free open-source models: better when you need a story arc, worse when you need a single perfect 10-second shot. Use both: write the script here, pay for one Sora clip if a specific shot needs to be magazine-quality.

Yes, POST /v1/video/movie/ with {idea, style, num_scenes, video_model}. Returns {output_url, scenes, share_url, tokens}. Heavy queued endpoint, expect 3-15 min depending on scene count + model. Bearer auth via developer keys. See /api/ for full snippets and the /v1/video/movie/status/ progress endpoint.

Rēhita utu kore: 30,000 token/rā

Hangaia he Kaute Kore Utu

Kāore he kāri ā-pūtea e hiahiatia ana

Ka pēhea tō whakatau i tēnei taputapu?

E hiahia ana Free.ai? Whakapāpāho ki ōna hoa!

E hiahiatia ana ētahi atu? Rēhita utu kore: 30,000 token/rā Whakawhanaunga i te wātea