VEED models API

Call 2 VEED models through one PopNow API key: VEED Dubbing Pro and VEED Dubbing. Prices start at $0.144 per second.

models: 2
endpoints: 2
starting price, per second: $0.144

VEED models

VEED Dubbing Proveed/dubbing-pro/video-translateNewStudio-grade dubbing with accents, voice match and lip syncVideoFrom$0.24per second
VEED Dubbingveed/dubbing/video-translateNewDub into 86 languages in each speaker’s voice, lips redrawnVideoFrom$0.144per second

Choosing VEED for video dubbing

Two dubbing tiers for talking clips

VEED supplies two video translation entries in the catalog, VEED Dubbing and VEED Dubbing Pro. Both take a talking clip up to ten minutes long, transcribe the speech, translate it and return the clip with a dubbed voice track. Both accept a short keyterms list of names and phrases that recognition must catch exactly as written, which matters for product names, people and places. The difference is in control and language coverage. The standard tier dubs into base languages without regional accents. Pro adds regional targets such as es-MX or pt-BR to choose an accent and a voice_clone_strength setting from 0 to 10 that decides how closely the dubbed voices follow each original speaker.

Choose a tier by audience and voice requirements

Use VEED Dubbing for internal updates, tutorials and drafts where a clear translated voice in the base language is enough. Use Dubbing Pro when the audience expects a regional accent, or when a presenter's own voice and delivery should carry into the new language; raise voice_clone_strength to keep more of the speaker's timbre and lower it for a cleaner neutral read. Both tiers are billed per second of the source clip, rounded up, and Pro costs more per second, so trim silence and intros before submitting. The PopNow video translator is a sibling worth comparing: it adds a glossary of fixed translations, a speaker count and an option to keep the background music under the dub.

Build the job so a reviewer can check it

Call /api/v1/jobs/createTask from your backend with a sk-popnow- key and the full public call name from the task reference. Set source_language explicitly when the clip has music under the voice or a strong accent, because automatic detection is the most common cause of a wrong transcript. Store the taskId with the source URL, the language pair, the keyterms and, for Pro, the voice strength. Fetch /api/v1/jobs/recordInfo or verify a completion webhook, then have someone who speaks the target language watch the whole clip. Check names, numbers and timing at sentence ends, and keep the original upload so a corrected keyterms list can be resubmitted without searching for the source.

VEED API prices

See pricing

Model	Best for	List price	PopNow price	You save
VEED Dubbing Pro`veed/dubbing-pro/video-translate`	Video Translator	—	$0.24per second
VEED Dubbing`veed/dubbing/video-translate`	Video Translator	—	$0.144per second

List prices are each maker's own published price for the same output, checked on Oct 14, 2026. Prices shown are starting prices; open a model for every tier.

Latest VEED additions

Changelog

Call a VEED model

The same request works for every model: change the model name and its input.

curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "veed/dubbing-pro/video-translate",
  "input": {
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "target_language": "af",
    "source_language": "auto"
  }
}'

import os, uuid, requests

res = requests.post(
    "https://api.popnow.ai/api/v1/jobs/createTask",
    headers={
        "Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "model": "veed/dubbing-pro/video-translate",
        "input": {
            "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
            "target_language": "af",
            "source_language": "auto"
        }
    },
    timeout=30,
)
body = res.json()
if body["code"] != 200:
    raise RuntimeError(f'{body["code"]} {body["msg"]}')
print(body["data"]["taskId"])  # poll this id, or wait for your callBackUrl

const res = await fetch("https://api.popnow.ai/api/v1/jobs/createTask", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.POPNOW_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    "model": "veed/dubbing-pro/video-translate",
    "input": {
      "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
      "target_language": "af",
      "source_language": "auto"
    }
  }),
});
const { code, msg, data } = await res.json();
if (code !== 200) throw new Error(`${code} ${msg}`);
console.log(data.taskId); // poll this id, or wait for your callBackUrl

Frequently asked questions

What is the difference between VEED Dubbing and Dubbing Pro?

Both dub a talking clip of up to ten minutes into another language. Pro adds regional language variants that pick an accent and a voice_clone_strength control for how closely each dubbed voice follows the original speaker. Pro also costs more per second of source video.

How long can a source clip be?

Each request accepts a talking clip of up to ten minutes with audible speech. Longer recordings should be split at natural pauses and submitted as separate jobs, then joined in your editor, so a problem in one section only requires that section to be redone.

How do I keep names and brand terms correct?

Pass them in keyterms, up to ten entries, spelled exactly as they should be heard. Recognition then treats them as fixed, which avoids a misheard product name being translated into an unrelated word. Review the first output and extend the list if a term still slips.

Should I set the source language or use auto?

Auto works for clean speech in a single language. Set the language explicitly when there is background music, a strong accent, long pauses or mixed languages, because a wrong detection produces a wrong transcript, and every later step translates that mistake faithfully.

How is VEED dubbing billed?

Billing is per second of the source clip, rounded up, with a higher per-second rate for Pro. Trimming silent openings, intros and outros before upload lowers the cost directly. The current rates are listed on each model reference page alongside the task schema.

Other model makers

All model makers

Start building in minutes

One key for every model, a USD balance you top up when you need to, and an exact price before every run.

Get API key Try in Playground