Introduction
VEED Dubbing Pro is VEED's studio tier for dubbing. It translates the speech in a clip, re-voices every speaker from a clone of their own voice, lets you pick a regional accent and redraws the lips so the new dialogue looks spoken.
Key features & highlights
Accents, not just languages
Send es-MX instead of es, or en-GB instead of en. Our Mexican Spanish run of a two-person dialogue was recognised by an independent transcriber as Mexican Spanish.
A dial for voice similarity
voice_clone_strength runs from 0 to 10. Seven, the default, keeps each speaker recognisable; push it to 10 for a near copy of the original voice, or towards 0 when the line should sound native.
Built for more than one speaker
VEED recommends this tier for interviews, panels and two-host formats. In our dialogue test each of the two speakers kept a separate voice and got their own lip movement.
Request parameters
| Parameter | Required | Description |
|---|---|---|
video_url | Yes | The footage to dub, up to 10 minutes, with speech you can hear. Upload the file or send a direct link to it; unreadable links are refused before any charge. at least 1 characters |
target_language | Yes | Required. A base language (94) or a regional accent (14), such as es-MX, pt-BR, en-GB or fr-CA. |
source_language | No | What is spoken in the clip. auto (the default) works it out; choose a language if it guesses wrong. |
voice_clone_strength | No | 0 to 10, default 7. Higher values keep more of each speaker's own voice and accent; lower values sound more native in the target language. |
keyterms | No | Up to 10 names or brief phrases for the transcription to spell exactly, each at most 50 characters and 5 words, with no < > { } [ ] or backslashes. at most 10 items |
Pricing
$0.24 / output second
Charged per second of the source clip with partial seconds rounded up, for clips up to 10 minutes. Before submission we hold the amount for an uploaded clip's real length, or for 10 minutes when you send a link, and release the difference at settlement. Accent, voice_clone_strength and keyterms are included in the price. A failed request costs nothing.
Use cases
Regional releases from one master
Cut a version for Spain and another for Mexico from the same footage, each with the accent its audience expects.
Shows with several hosts
Podcasts and panels filmed on camera reach new markets with every host still sounding like themselves.
Prompt guide & pro tips
Choose the accent the audience speaks
A regional code only matters where the language has variants. For German or Japanese the base code is all there is, and a region tag is ignored.
Start at the default strength
Run the first take at 7. If the dub carries too much of the original accent, lower it a step or two; if a speaker no longer sounds like themselves, raise it.
Light the faces
The mouth match depends on seeing the mouth. Close and medium shots with clear faces give the strongest effect.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "veed/dubbing-pro/video-translate",
"input": {
"source_language": "auto",
"target_language": "af",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.
