OrcaDub 1.0 is an end-to-end, prosody-aware dubbing and video-translation model. Given a source video, it produces a dubbed video in a target language in the original speakers' cloned voices, preserving delivery — emphasis, pauses, intonation — and word-level timing. It covers 28 languages in any direction, clones a separate voice per speaker in multi-speaker footage, preserves background music and ambience, and aligns the dub to the source at word level. It is reachable from the free web Studio and from an OpenAI-compatible API.
OrcaDub 1.0 is an end-to-end, prosody-aware dubbing and video-translation model, released July 2026. Given a source video it produces a dubbed video in a target language, spoken in the original…
28 languages, any direction. Multi-speaker videos with per-speaker voice cloning. Background music and ambience preservation. Optional song translation. Word-level alignment to the source timing. Loudness-normalized output (EBU R128).
Languages: 28, any direction. Input: video upload or URL (YouTube, TikTok, or a direct link). Output: dubbed mp4, loudness-normalized. Access: web Studio and OpenAI-compatible API, model id orca/dub. Watermark: on for free dubs, controllable per job via the API watermark switch. Erasing watermarks or subtitles already burnt into the source video is a separate paid add-on.
Heavily overlapping speakers can reduce separation and cloning quality. Singing is supported behind an explicit switch and remains harder than speech. Very dense dialogue may be compressed to hold sync; every line can be corrected in the Studio. Culture-specific wordplay may be adapted for meaning rather than translated literally.
OrcaDub bills per minute of dubbed video, not per API call: $0.60 per minute, charged per started minute, with partial minutes rounding up. Every workspace starts with 10 free minutes; free dubs carry a small watermark and each free dub is capped at 2 minutes per clip. Watermark removal and subtitle removal are optional add-ons on top of the per-minute price, charged per started minute and priced by the source video short side. Current per-resolution rates are on the OrcaDub pricing page.
OrcaDub is reachable two ways. The free web Studio takes a video upload or a URL, runs the dub, and lets you retranslate, retime and re-voice any line before export. The OpenAI-compatible API exposes the same model under the id orca/dub through OrcaRouter, with a per-job watermark switch on the output.
By default, voice cloning operates on the voices present in the uploaded video; project workflows can additionally reuse character voices you've saved. Free dubs carry a watermark; API output supports watermarking via the watermark switch. Dubbing content you don't hold rights to, or cloning a voice without the speaker's consent, violates the terms of use and leads to account termination.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.orcarouter.ai/v1",
api_key=os.environ["ORCAROUTER_API_KEY"],
)
response = client.chat.completions.create(
model="orca/dub",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)| Per minute | $0.6000 |
| Currency | USD |
| Billed per started minute of output, not per API call | |
What developers are saying this week
@misc{orcarouter_dub,
title = {OrcaDub 1.0 API},
author = {OrcaDub},
year = {2026},
howpublished = {OrcaRouter},
url = {https://www.orcarouter.ai/models/orca/dub}
}OrcaDub. (2026). OrcaDub 1.0 API. OrcaRouter. https://www.orcarouter.ai/models/orca/dub