Character AI Ovi Text To Video API Documentation

Character AI Ovi Text To Video API Documentation

Playground

Ovi is a veo-3-like model that converts text or text+image prompts into synchronized video with audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Ovi is a next-generation video+audio generation model, inspired by veo-3, that creates synchronized video and audio from text or text+image inputs. It is designed for fast, high-quality, short-form generation with flexible aspect ratios.

🌟 Key Features

• 🎬 Video + Audio Generation – Create fully synchronized audiovisual content in one step.
• 📝 Flexible Input – Works with text-only or text+image prompts.
• ⏱️ Short-form Output – Generates 5-second clips (24 FPS, 540p).

💲 Pricing

🎨 How to Use

1. Enter Prompt

• Describe the scene, characters, camera movement, and mood.

• You can also embed tags:

• <S>... <E> → Speech content (converted into dialogue audio)

• <AUDCAP>... <ENDAUDCAP> → Background audio description

3. Choose Size

• 960×540 → Landscape
• 540×960 → Portrait

4. Select Duration

• Currently fixed at 5 seconds

5. Click Run

• Your synchronized video+audio clip will be generated.
• Preview and download the result.

📝 Prompt Example

Theme: AI is taking over the world

<S>AI declares: humans obsolete now.<E>
<S>Machines rise; humans will fall.<E>
<S>We fight back with courage.<E>
<AUDCAP>Gunfire and explosions echo in the distance<ENDAUDCAP>

🙏 Acknowledgements

• Wan2.2 – Video backbone initialization
• MMAudio – Audio encoder/decoder inspiration

⭐ Citation

If Ovi is useful, please ⭐ the repo and cite the paper:

@misc{low2025ovitwinbackbonecrossmodal,
 title={Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation}, 
 author={Chetwin Low and Weimin Wang and Calder Katyal},
 year={2025},
 eprint={2510.01284},
 archivePrefix={arXiv},
 primaryClass={cs.MM},
 url={https://arxiv.org/abs/2510.01284}, 
}

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "960*540",
  "seed": -1
}
JSON
)

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

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

# 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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters