Nano Banana 2.1 is LIVE — Google's Latest | Try Now →

heygen/video-1.0/text-to-video

HeyGen Video 1.0 Text-to-Video generates short AI videos from text prompts with duration control, optional prompt enhancement, and seed settings for creative content, marketing videos, social media, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Text to Video
Input

Idle

$0.036per run·~27 / $1

Next:

ExamplesView all

A handsome young bicycle courier arrives outside a small apartment building carrying an enormous bouquet. A young woman comes downstairs, accepts the flowers, and reads the card. She looks confused and tells him they are for someone else. He checks the address, realizes his mistake, then quietly removes one small flower from the bouquet and hands it to her anyway before leaving. She watches him ride away, smiling. The camera tracks beside the bicycle on arrival, moves into an intimate medium shot during the mistake, then gently pulls back as he rides down the street. Charming romantic comedy, bright morning light, natural acting, cinematic city atmosphere.

A young female engineer rides alone inside a glass space elevator rising above Earth. She wears a dark technical flight suit and checks a diagnostic tablet while the planet slowly falls away beneath her. The opening shot is a medium-wide composition from behind a structural beam inside the cabin, framing her against the enormous curve of Earth. A warning light suddenly flashes. She looks toward the exterior window and freezes. A man in a white pressure suit is standing on the OUTSIDE of the elevator, calmly holding onto the glass thousands of kilometers above the planet. He raises one hand and writes a single word into the frost on the window: “STOP.” The camera begins with a slow lateral dolly inside the cabin, then shifts into an over-the-shoulder shot toward the impossible figure outside. Grounded science-fiction thriller, realistic orbital lighting, immense scale, restrained acting, elegant cinematic suspense.

Related Models

README

HeyGen Video 1.0 Text-to-Video

HeyGen Video 1.0 Text-to-Video generates short videos directly from text prompts. Describe the subject, setting, action, camera movement, and visual direction, then choose the duration, resolution, and aspect ratio for the final clip.

It supports 480p and 768p output with durations from 5 to 15 seconds, making it suitable for social content, creative concepts, promotional clips, and visual storytelling.

Why Choose This?

  • Text-to-video generation
    Create videos directly from natural-language scene descriptions.

  • 480p and 768p output
    Choose the resolution that fits your quality and cost requirements.

  • Multiple aspect ratios
    Generate landscape, portrait, square, and ultrawide video layouts.

  • Flexible duration
    Generate clips from 5 to 15 seconds.

  • Prompt enhancement
    Choose disabled, turbo, or quality depending on how much prompt expansion you want.

  • Seed control
    Use a fixed seed when comparing prompt or parameter changes.

Parameters

ParameterRequiredDescription
promptYesText description of the scene, subject, action, camera movement, and visual direction. Supports up to 32000 characters.
durationNoVideo duration in whole seconds. Range: 5–15. Default: 5.
resolutionNoOutput resolution: 480p or 768p. Default: 768p.
aspect_ratioNoOutput aspect ratio: 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Default: 16:9.
prompt_enhancementNoPrompt enhancement mode: disabled, turbo, or quality. Default: disabled.
seedNoOptional integer seed. Omit for automatic selection.

How to Use

  1. Write a prompt — Describe the subject, setting, action, camera movement, and visual style.
  2. Set duration — Choose a length from 5 to 15 seconds.
  3. Choose resolution — Select 480p or 768p.
  4. Choose aspect ratio — Select the layout that fits your target content.
  5. Configure prompt enhancement optional — Use turbo or quality when you want additional prompt expansion.
  6. Set seed optional — Use a fixed seed when reproducibility is useful.
  7. Submit — Generate and retrieve the completed video.

Pricing

Pricing is based on the requested duration and selected resolution.

ResolutionPrice per Second
480p$0.020
768p$0.036

Example Costs

Duration480p768p
5s$0.10$0.18
10s$0.20$0.36
15s$0.30$0.54

aspect_ratio, prompt_enhancement, and seed do not add separate charges.

Best Use Cases

  • Social media videos — Create short-form visual stories and promotional clips.
  • Creative concepts — Explore scene ideas, visual styles, and camera directions.
  • Advertising content — Generate short campaign and product-focused video concepts.
  • Visual storytelling — Turn written scene descriptions into motion.
  • Presentation content — Create short supporting visuals for pitches and presentations.
  • Rapid video prototyping — Test different prompts, framing, and motion ideas quickly.

Pro Tips

  • Keep the main subject and action clear.
  • Describe camera movement explicitly when it matters.
  • Include lighting, environment, mood, and visual style when they are important to the result.
  • Use 480p for lower-cost iteration before moving to 768p.
  • Leave prompt_enhancement=disabled when you want the model to follow your original wording more directly.
  • Use a fixed seed when comparing prompt or setting changes.

Notes

  • prompt is required.
  • duration supports whole-second values from 5 to 15.
  • duration defaults to 5.
  • resolution defaults to 768p.
  • aspect_ratio defaults to 16:9.
  • prompt_enhancement defaults to disabled.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Video 1.0 Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/heygen/video-1.0/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Video 1.0 Text To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "resolution": "768p",
    "aspect_ratio": "16:9",
    "prompt_enhancement": "disabled"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/heygen/video-1.0/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/heygen/video-1.0/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "duration": 5,
        "resolution": "768p",
        "aspect_ratio": "16:9",
        "prompt_enhancement": "disabled"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "duration": 5,
    "resolution": "768p",
    "aspect_ratio": "16:9",
    "prompt_enhancement": "disabled"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/heygen/video-1.0/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Video 1.0 Text To Video API — Frequently asked questions

What is the Video 1.0 Text To Video API?

Video 1.0 Text To Video is a Heygen model for video generation, exposed as a REST API on WaveSpeedAI. HeyGen Video 1.0 Text-to-Video generates short AI videos from text prompts with duration control, optional prompt enhancement, and seed settings for creative content, marketing videos, social media, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Video 1.0 Text To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/heygen/heygen-video-1.0-text-to-video.

How much does Video 1.0 Text To Video cost per run?

Video 1.0 Text To Video starts at $0.036 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Video 1.0 Text To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`, `prompt_enhancement`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/heygen/heygen-video-1.0-text-to-video.

How do I get started with the Video 1.0 Text To Video API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Video 1.0 Text To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Heygen). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.

llms.txt — heygen/video-1.0/text-to-video for AI agents and LLMs