Dubbing API
Make your video speak any language

How we compare

Video dubbing is sold as a credit-based studio product (ElevenLabs Dubbing), a subscription localisation suite (Rask), or an avatar-video platform where dubbing is one feature among many (HeyGen). The hyperscalers ship the building blocks — transcription, translation, speech synthesis — but no single API that runs the whole dubbing pipeline. Brainiall is one REST call: submit a video, poll a job, get a dubbed video back — self-serve from the first call, priced per minute.

Prices are list-price approximations for orientation, not quotes — most dubbing vendors price by subscription or credits, so per-minute figures are estimates. Always check each vendor's current terms.

Pricing

One per-minute price for the whole pipeline — transcription, translation, synthesis and remux included. The free tier is enough to dub real clips end to end and wire dubbing into a workflow.

PAYG: $0.30 / minute of processed video (Brainiall Dubbing engine). The /preview endpoint and job-status polling are always free — you only pay when you create a dub. No minimum spend, no contract — the same single API key and usage-based billing as the rest of the catalog.

Three endpoints

# Submit a video as raw bytes, a multipart file upload, or {"video": "<base64>"}.

# 1. Create — submit a video, get a job_id back immediately
POST https://api.brainiall.com/v1/dubbing/create
  body: {"video": "<base64>", "target_lang": "pt", "source_lang": "en"}
  -> {"job_id": "a1b2c3d4", "status": "queued",
      "poll_url": "/v1/dubbing/job/a1b2c3d4",
      "engine": "Brainiall Dubbing engine"}

# 2. Job — poll until the dubbed video is ready (polling is free)
GET https://api.brainiall.com/v1/dubbing/job/a1b2c3d4
  -> {"status": "completed", "progress": 1.0, "duration_s": 92.4,
      "segment_count": 24,
      "result": {"dubbed_video": "<base64 mp4>", "target_lang": "pt",
                 "segments": [{"start": 0.0, "end": 3.2,
                               "original_text": "Welcome to the demo.",
                               "translated_text": "Bem-vindo a demonstracao.",
                               "voice": "af_heart"}]}}

# 3. Preview — fast translated-transcript preview, no render (free)
POST https://api.brainiall.com/v1/dubbing/preview
  body: {"video": "<base64>", "target_lang": "pt"}
  -> {"source_lang": "en", "target_lang": "pt",
      "segments": [{"start": 0.0, "end": 3.2,
                    "original_text": "Welcome to the demo.",
                    "translated_text": "Bem-vindo a demonstracao."}]}

create is asynchronous: it returns a job_id instantly and renders in the background, so a long video never blocks your request. Poll job for progress until status is completed — polling never counts against your quota.

How dubbing works

One create call runs the whole pipeline. Every stage is explainable — the finished job hands back the per-segment transcript and translation it used.

• Transcribe with timing. The original audio track is transcribed to word-level timestamps, then grouped into natural speech segments at sentence and pause boundaries.
• Translate segment by segment. Each segment is translated into the target language independently, so timing and meaning stay aligned.
• Synthesize and time-fit. Target-language speech is synthesized for each segment and time-fitted so it lands in the original segment's slot — a translation that would overrun is gently compressed rather than allowed to drift.
• Multi-speaker aware. With diarization enabled, each speaker keeps a distinct voice across the whole video.
• Remux, original video untouched. The new audio track is muxed onto the original video stream — the picture is copied through, never re-encoded.

What it's for

• Marketing & growth: localise launch videos, ads and social clips into every market you sell in — without a studio booking.
• Courses & training: take one recording of a lesson or onboarding module and ship it in every language your learners speak.
• Product & demos: dub walkthroughs and release videos so every region sees the product in its own language.
• Media & creators: re-voice long-form video and podcasts to reach audiences beyond the original language.
• Accessibility & reach: pair the per-segment transcript with the dubbed track for subtitles and searchable copy in both languages.
• One bill, one key: same Brainiall API key and usage-based billing as the rest of the catalog — no separate dubbing vendor to procure.

Press kit & resources

What reviewers, integrators and procurement teams typically ask for.

More specialty APIs

Same single API key, same usage-based pricing, different problem solved.

Content ModerationText & image policy screening

Document AIOCR & structured extraction from documents

Vision LabelsObject & scene tagging for images

Identity VerificationFace match, liveness & deepfake checks