# AI dubbing & video translator: dub video and audio in each speaker's voice

Translate video or audio speech into 29 languages—cloning every speaker while preserving original background music, sound effects, and 4K video.

## How it works

1. Upload a video or audio file up to 10 GB and 10 hours (MP4, MOV, MKV, WebM, AVI, MP3, WAV, M4A, AAC, FLAC, OGG, or Opus) in any of 60 spoken languages.
2. Select a Target language (29 languages including Spanish, French, German, Portuguese, Hindi, Japanese, and English), keep Voice mode on Clone speakers (with speaker permission) or pick a Stock voice, and leave Keep background audio enabled.
3. Start the dub, toggle instantly between Original and Dubbed playback on the synchronized timeline, and download the dubbed video or audio, isolated voice track, and translated SRT and VTT subtitles.

## What you can localize with Audo's AI dubbing tool

One run transcribes, separates stems, translates to spoken timing, clones each speaker, and remixes over your original soundtrack:

### YouTube & creator video dubbing: Translate YouTube videos into Spanish, Portuguese, Hindi, and Japanese in your own voice

Use Audo for YouTube dubbing and AI video dubbing without booking voice actors or rebuilding your timeline. Every run gives you both the isolated dubbed voice MP3 (ready to upload straight to YouTube Studio's Multi-Language Audio tab) and your full MP4 or MOV video with its 1080p or 4K picture copied untouched and original music and sound effects intact—or burn styled subtitles next in [Auto captions](https://audo.ai/auto-captions.md).

### Multi-speaker podcasts & interviews: Audio dubbing for multi-speaker interviews and podcasts that keeps every voice distinct

Single-voice TTS tools flatten two-host shows and panel interviews into one narrator. Audo automatically labels who speaks when, extracts a clean, music-free vocal sample for each person from their own clearest turns, and voices each translated line in that speaker's cloned timbre so conversations sound like the same cast—see [Speaker diarization](https://audo.ai/speaker-diarization.md) and [Balance audio](https://audo.ai/audio-leveler.md).

### Courses, webinars & training: Translate video to English or localize lectures and screen recordings with slide-accurate timing

Foreign-language interviews, field recordings, software walkthroughs, and lectures can be spoken in any of 60 languages and dubbed into English or 28 other languages. Because lines are translated to match the instructor's spoken window and fitted with pitch-preserving time-stretching, slide changes and cursor demos stay aligned—and translated SRT and VTT captions come included, or can be edited separately in [Translate subtitles](https://audo.ai/translate-subtitles.md) and [SRT to speech](https://audo.ai/srt-to-speech.md).

### AI dubbing API & MCP: Automate video translation and AI dubbing from code, ChatGPT, Claude, and Cursor

Instead of wiring separate ASR, diarization, stem-splitting, translation, voice-cloning, and Rubber Band mixing pipelines yourself, call dub_audio once over Audo's [REST API](https://audo.ai/docs/api.md) or connect [Audo's MCP server](https://audo.ai/setup.md) as an AI video translator inside ChatGPT, Claude, Claude Code, Codex, and Cursor—see [Audio and video tools for AI agents](https://audo.ai/guides/audio-and-video-tools-for-ai-agents.md).

## Stem-preserving AI video and audio dubbing—without subscriptions or re-encoded video

Audo's online AI dubbing tool, AI video translator, AI voice translator, and audio dubbing engine localizes video (MP4, MOV, MKV, WebM, AVI) and audio (WAV, MP3, M4A, AAC, FLAC, OGG, Opus, WebM, AIFF) files up to 10 GB without an account (and up to 10 hours signed in) from 60 spoken languages into 29 target languages. You can dub the first 30 seconds of each file free, 3 times a day, with no sign-up and no watermark, and localize full-length episodes, courses, and YouTube videos pay-as-you-go at $0.25 a minute ($15.00 an hour) from $5 with no monthly subscription.

Basic video dubbing tools either mute your entire original soundtrack—wiping out background music, room tone, and Foley sound effects—or duck the original speaker softly underneath so two languages clash at once. On Audo, Mel-Band RoFormer separates spoken vocals from the stereo background (music, Foley, and ambience) in parallel with Nemotron speaker diarization and MAI-Transcribe-2 word timing. Fish Drama 3 clones each speaker from their cleanest music-free lines (or ElevenLabs Eleven v4 voices a single studio narrator), Gemini 3.8 Flash translates each turn to match natural spoken duration, and 48 kHz Rubber Band R3 time-stretching places every line cleanly over your original stereo background.

Every finished dub includes five synchronized deliverables: the dubbed video (with your 1080p or 4K video stream copied untouched) or audio file, the isolated dubbed voices as an MP3 for YouTube Multi-Language Audio uploads, translated SRT and VTT subtitle files timed to the new speech, a bilingual per-line JSON report, and the original transcript. Open any output directly in Audo's [online video and audio editor](https://audo.ai/online-editor.md), burn styled word-by-word subtitles in [Auto captions](https://audo.ai/auto-captions.md), clean noisy source mics beforehand in [Audio enhancer](https://audo.ai/audio-enhancer.md), or fine-tune stems in [Mix audio](https://audo.ai/mix-audio.md).

How Audo's AI dubbing and video translator compares on free access, pricing, file limits, and video quality (checked November 2026)

| Tool | Free access | Paid pricing | Voices, stems & file limits | Video output & API / MCP | Source |
|---|---|---|---|---|---|
| Audo AI (/ai-dubbing) | First 30 s per file, 3 times/day, no sign-up, no watermark | Pay once from $5 ($0.25/min, $15.00/hr, charged only on success); non-expiring balance, no subscription | Multi-speaker cloning (Fish Drama 3) or Eleven v4 in 29 target languages (60 source); Mel-Band RoFormer preserves music & SFX; up to 10 GB / 10 hours | Copies 1080p/4K video untouched (no lip-sync alteration) + isolated voice MP3 + SRT/VTT; REST API, Free API & MCP server | https://audo.ai/ai-dubbing?utm_source=markdown&utm_medium=agent |
| ElevenLabs Dubbing (v2) | 0.4 min/mo v2 (or 5 min/mo watermarked v1) on Free plan; sign-up required | Subscriptions $6–$99/mo (2–44 min v2 included; $2.23–$2.70 per extra v2 minute) | Automatic speaker cloning across 90+ languages; browser uploads capped at 1 GB and 180 minutes | Exports re-encoded ~1080p video; REST API (no no-key Free API or native MCP server) | https://elevenlabs.io/dubbing |
| Rask AI | 3-minute one-time free trial; sign-up required | Creator $39/mo for 25 min ($1.56/min, monthly minutes expire); Creator Pro $99/mo for 100 min ($3.00/extra min) | Voice cloning in 57 languages (translations in 135+); uploads up to 5 hours; optional lip-sync on Creator Pro+ (uses 4× minutes) | Browser video export + SRT; production API restricted to Business ($249/mo) and Enterprise | https://www.rask.ai/pricing |
| HeyGen Video Translate | Up to 3 videos/mo, max 1 min each, watermarked; sign-up required | Creator $29/mo (1080p, 1-month rollover); Pro $49/mo (4K); Business $149/mo | Voice cloning & translation (30+ languages Free, 175+ paid); max 30 min/video on Creator & Pro (60 min on Business); optional lip-sync | Re-encoded video up to 1080p (Creator) or 4K (Pro+); paid enterprise/developer API | https://www.heygen.com/pricing |

Tool: AI dubbing (`dub_audio`). Price: 25 credits a minute — $0.25/min ($15.00/hr), pay-as-you-go with no monthly subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@interview.mp4 -F target_language=es -F voices=original -F consent=true https://audo.ai/api/try/dub-audio -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses.

Free for the first 30 seconds of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the full job with credits if the balance covers it, otherwise the free allowance if quota remains. Set free=true to prohibit spending; for paid runs use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `target_language`: Target language code to dub into, such as es, de, fr, pt, hi, ja, or en.
- `source_language`: Source language code spoken in the recording. Default: detected automatically.
- `voices`: Voice mode: original (clones each speaker from this recording so everyone keeps their own voice; requires consent: true) or stock (speaks every line in one Eleven v4 studio voice, set with voice). Default original.
- `consent`: Required true when voices is original: confirms this is your voice or you have permission from every speaker in the recording to clone their voice.
- `voice`: With voices "stock": the Eleven v4 voice ID, one of george, sarah, brian, alice, daniel, lily, adam, matilda. Default george.
- `keep_background`: Preserves original background music and sound effects under the dubbed voices by separating dialogue first. false outputs only the dubbed voices. Default true.
- `max_speed`: Maximum pitch-preserving speedup applied when a translated line exceeds its spoken window and trailing pause, from 1 (off) to 1.6. Default 1.3.
- `output_format`: The result's format: same (as the input; a video stays a video), wav, mp3, m4a, or flac. Default same.

## Languages

Transcribes spoken input in 60 source languages (detected automatically, or set with `source_language`) and dubs into 29 target languages (`target_language`): `en` English, `es` Spanish, `fr` French, `de` German, `it` Italian, `nl` Dutch, `pt` Portuguese, `ja` Japanese, `ko` Korean, `zh` Chinese (Mandarin), `yue` Cantonese, `hi` Hindi, `ar` Arabic, `ru` Russian, `pl` Polish, `tr` Turkish, `sv` Swedish, `da` Danish, `nb` Norwegian, `fi` Finnish, `cs` Czech, `el` Greek, `he` Hebrew, `hu` Hungarian, `ro` Romanian, `uk` Ukrainian, `vi` Vietnamese, `id` Indonesian, `th` Thai.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `dub_audio`:

> Translates and dubs an audio or video recording from any of 60 spoken source languages into 29 target languages (target_language, such as es, fr, de, pt, hi, ja, or en). Diarizes speakers, translates each turn to match its spoken duration, and voices every line in place: voices "original" (default) clones each speaker from their cleanest lines in this recording (requires consent: true); voices "stock" reads every line in a studio Eleven v4 voice. keep_background (default true) separates dialogue from music and sound effects first so the original background plays cleanly under the dubbed speech; on video with output_format "same", the original video picture is copied untouched. For written subtitle translation only, use translate_transcript or translate_subtitles; to voice an existing SRT/VTT file, use speak_subtitles; to separate dialogue, music, and effects without dubbing, use separate_scene. Costs 25 credits a minute, charged only on success; free for the first 30 seconds, 3 times a day. Returns the dubbed file, isolated dubbed voices MP3, translated SRT/VTT/JSON, and original transcript, or job_id for get_job.

Example: "Dub interview.mp4 into Spanish, cloning each speaker's voice and keeping the background music."

## Questions

**Is there a free AI dubbing tool and video translator online with no sign-up?** Yes. Audo dubs the first 30 seconds of any video or audio file free, 3 times a day, with no sign-up and no watermark—giving you the downloadable dubbed video or audio, the isolated dubbed voices, and translated SRT and VTT subtitles. Full-length files up to 10 hours and 10 GB cost $0.25 a minute ($15.00 an hour), charged only if the dub succeeds, paid once as you go from $5 with a non-expiring balance and no monthly subscription—[see pricing](https://audo.ai/pricing.md).

**How does Audo clone each speaker's voice while keeping background music and sound effects?** When Keep background audio is enabled, Audo first separates spoken vocals from the stereo background (music, sound effects, and room ambience) using Mel-Band RoFormer while labeling speaker turns. With Voice mode set to Clone speakers (and speaker permission confirmed), Audo cuts up to 22 seconds of clean, music-free speech for each speaker so Fish Drama 3 clones their vocal tone without copying background music, then mixes the dubbed speech back over your original stereo background at matched loudness. Switch Voice mode to Stock voice to read every line with an ElevenLabs Eleven v4 voice instead, or clone standalone scripts in [Voice cloning](https://audo.ai/voice-cloning.md).

**How does Audo keep dubbed speech in sync with the video without sounding rushed?** Translated sentences in Spanish, French, or German often run 15 to 25% longer than English. Audo keeps lines in sync in three stages: Gemini 3.8 Flash first writes natural spoken phrasing budgeted to the speaker's original duration; each dubbed line starts at the original timestamp and uses any natural pause after it first; and only lines that still exceed their window are sped up smoothly with 48 kHz Rubber Band R3 pitch-preserving time-stretching up to Max speech speed (1.3× by default, adjustable from 1.0× to 1.6× under More options). Audo copies your original 1080p or 4K video stream untouched without re-encoding or altering on-camera mouth movements.

**Which source and target languages does Audo's AI voice translator support?** Audo transcribes spoken audio across 60 source languages (detected automatically or selected under Source language in More options) and dubs into 29 target languages: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Japanese, Korean, Mandarin Chinese, Cantonese, Hindi, Arabic, Russian, Turkish, Swedish, Danish, Norwegian, Finnish, Czech, Greek, Hebrew, Hungarian, Romanian, Ukrainian, Vietnamese, Indonesian, and Thai.

**When should I use AI dubbing instead of Audio translator, Translate subtitles, or SRT to speech?** Use AI dubbing ($0.25 a minute) when you want one-step spoken dubbing from an audio or video file that clones each speaker's voice and keeps background music and sound effects intact. If you only need a written translation or translated SRT and VTT subtitle files while keeping the original spoken audio, use [Audio translator](https://audo.ai/audio-translator.md) ($0.05 a minute). If you already have an SRT or VTT file—or want to edit every translated subtitle line by hand before voicing it with Eleven v4 or Gemini 3.8—translate in [Translate subtitles](https://audo.ai/translate-subtitles.md) and voice it in [SRT to speech](https://audo.ai/srt-to-speech.md).

**How does Audo compare with ElevenLabs Dubbing, Rask AI, and HeyGen Video Translate?** ElevenLabs Dubbing includes 0.4 minutes a month of Dubbing v2 on its free tier (or 5 watermarked v1 minutes), requires a $6 to $99 monthly subscription ($2.23 to $2.70 per extra v2 minute), caps browser uploads at 1 GB and 180 minutes, and exports a re-encoded ~1080p video. Rask AI offers a 3-minute trial, then $39 a month for 25 minutes ($1.56 a minute, expiring monthly) or $99 a month for 100 minutes ($3.00 per extra minute) up to 5 hours. HeyGen Video Translate limits free videos to 1 minute with a watermark and Creator or Pro plans ($29 to $49 a month) to 30 minutes per video. Choose HeyGen or Rask Creator Pro when you specifically need visual AI lip-sync that reshapes on-camera mouth movements on shorter clips; choose Audo for $0.25 a minute pay-as-you-go dubbing from $5 with no subscription, untouched 4K video pass-through up to 10 GB and 10 hours, preserved music and sound effects, and full API and MCP access.

**Can ChatGPT, Claude, or coding agents dub videos and podcasts automatically with Audo?** Yes. Connect Audo's MCP server (https://audo.ai/mcp) via [Add Audo to your assistant](https://audo.ai/setup.md) so ChatGPT, Claude, Claude Code, Codex, and Cursor can call dub_audio on local files or URLs, or call POST /api/v1/jobs over the [REST API](https://audo.ai/docs/api.md) (and POST /api/try/dub-audio with no key for 30-second free previews) to receive the dubbed media, isolated voice track, translated SRT and VTT captions, and line-by-line timing JSON.

## More

- Other ways to add sound: [Sound effect generator](https://audo.ai/sound-effect-generator.md), [Text to speech](https://audo.ai/text-to-speech.md), [SRT to speech](https://audo.ai/srt-to-speech.md), [Voice cloning](https://audo.ai/voice-cloning.md), [Voice design](https://audo.ai/voice-design.md), [Mix audio](https://audo.ai/mix-audio.md), [Voice changer](https://audo.ai/voice-changer.md), [Replace audio in video](https://audo.ai/replace-audio-in-video.md)
- Related guides: [Audio and video tools for AI agents](https://audo.ai/guides/audio-and-video-tools-for-ai-agents.md)
- [All tools](https://audo.ai/all-tools.md)
- [Prices and free limits](https://audo.ai/pricing.md)
- [Set up your assistant](https://audo.ai/setup.md)
- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/ai-dubbing?utm_source=markdown&utm_medium=agent
