[{"data":1,"prerenderedAt":54},["ShallowReactive",2],{"blog-post-ai-dubbing-in-your-own-voice":3,"blog-index":15},{"slug":4,"title":5,"description":6,"date":7,"updated":7,"tags":8,"image":12,"html":13,"reading_minutes":14},"ai-dubbing-in-your-own-voice","New: AI dubbing, in your own voice, and text read aloud","Dub a video into 48 languages, in an AI voice or your own, or turn text into an MP3. How it works, what it costs, and what changed in our Terms.","2026-10-28",[9,10,11],"dubbing","video","subtitles","https:\u002F\u002Fcontent.presentr.me\u002Fanalyze\u002Fassets\u002Fog.44ac3e4fbb.png","\u003Cp>Presentr Analyze has made captions and translated subtitles for a while. Now it can speak them: three new things you can do today.\u003C\u002Fp>\n\u003Ch2 id=\"1-dub-a-video\">1. Dub a video\u003C\u002Fh2>\n\u003Cp>Upload a video or paste a link, and pick a language. Analyze transcribes it, translates the captions, and reads the translation aloud, each line timed to when it's said in the original, over the original sound turned down.\u003C\u002Fp>\n\u003Cp>You get:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>the translated subtitles (SRT and VTT);\u003C\u002Fli>\n\u003Cli>a dubbed audio track (MP3);\u003C\u002Fli>\n\u003Cli>a dubbed video (MP4).\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>A few things worth knowing before you start:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>48 languages.\u003C\u002Fstrong> Seven of our translation languages can't be spoken yet (Bengali, Georgian, Gujarati, Malayalam, Punjabi, Albanian and Telugu); the run page says so.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Up to 60 minutes\u003C\u002Fstrong> per video.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Long lines.\u003C\u002Fstrong> When a translated line is longer than the original, it first uses the pause before the next line, then is sped up slightly (never past about 1.3x). A line that still doesn't fit is cut short, and the run page tells you how many, so you can shorten the translation and dub again.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>The original sound stays, quieter.\u003C\u002Fstrong> Music and effects are kept under the new voice; the original speech is still faintly audible.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Price:\u003C\u002Fstrong> 4 credits a minute in all: 1 to transcribe, 1 to translate, 2 to dub. The dub is charged only when it's delivered; if it fails, you're not charged.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Already have a translated run? Open its Subtitles tab and choose \u003Cstrong>Dub into …\u003C\u002Fstrong>.\u003C\u002Fp>\n\u003Ch2 id=\"2-in-your-own-voice\">2. In your own voice\u003C\u002Fh2>\n\u003Cp>Record or upload 10 to 30 seconds of yourself speaking, and Analyze can dub your videos in your voice.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>It works for \u003Cstrong>English, Spanish, French, German, Italian and Portuguese\u003C\u002Fstrong>. Other languages use one of the four AI voices.\u003C\u002Fli>\n\u003Cli>It costs the same as the AI voices.\u003C\u002Fli>\n\u003Cli>Add a voice in \u003Cstrong>Settings → Voices\u003C\u002Fstrong>, or from the voice menu when you dub. You'll be asked to confirm that it's your voice, or that you have the speaker's permission.\u003C\u002Fli>\n\u003Cli>A voice lasts \u003Cstrong>60 days\u003C\u002Fstrong>, after which you record it again. You can delete it at any time, which deletes the copy of your voice and your recording straight away (a voice that a dub is still using can be deleted once the dub finishes).\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2 id=\"3-read-text-aloud\">3. Read text aloud\u003C\u002Fh2>\n\u003Cp>Paste a script, a lesson or a letter on the new \u003Cstrong>Read aloud\u003C\u002Fstrong> page and get it back as an MP3, in an AI voice or your own. Up to 50,000 characters at a time (about 55 minutes of audio). It's 2 credits per minute of audio; you see an estimate before you start, and you're charged on the real length, never more than the estimate.\u003C\u002Fp>\n\u003Ch2 id=\"what-changed-in-our-terms-and-privacy-policy\">What changed in our Terms and Privacy Policy\u003C\u002Fh2>\n\u003Cp>Because \"My voice\" makes a synthetic copy of a real person's voice, we've added rules for it. In short:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Terms, new section 12 (Voice cloning).\u003C\u002Fstrong> Only add your own voice, or a voice you have the speaker's express permission to use. Don't use a cloned voice to impersonate anyone, deceive, make someone appear to say something they didn't agree to, or in misleading political content. Tell your audience the audio is AI-generated where the law or the context calls for it. We can remove a voice, or suspend an account, if a voice is misused. Later sections were renumbered.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Privacy Policy.\u003C\u002Fstrong> A new section explains what we keep when you add a voice: the recording (until you delete the voice), its name and language, and a record of your consent (its wording, time, IP address and browser), which we keep for up to three years after the voice is deleted as evidence that consent was given. The list of services now says that AssemblyAI creates and speaks cloned voices, and that OpenAI speaks the AI voices.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Nothing changed for features you already use. Read the full \u003Ca href=\"https:\u002F\u002Fanalyze.presentr.me\u002Fterms#voice-cloning\" rel=\"noopener\">Terms\u003C\u002Fa> and \u003Ca href=\"https:\u002F\u002Fanalyze.presentr.me\u002Fprivacy#voice-samples\" rel=\"noopener\">Privacy Policy\u003C\u002Fa>, and if something here doesn't work the way it should, email \u003Ca href=\"mailto:hello@presentr.me\">hello@presentr.me\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fanalyze.presentr.me\u002Ffeatures\u002Fai-dubbing\" rel=\"noopener\">Dub a video\u003C\u002Fa>\u003C\u002Fp>\n",3,{"site":16,"generated_at":17,"posts":18,"redirects":53},"analyze","2026-10-28T19:21:01.314Z",[19,22,33,44],{"slug":4,"title":5,"description":6,"date":7,"updated":7,"tags":20,"image":12,"url":21,"published_at":17},[9,10,11],"https:\u002F\u002Fanalyze.presentr.me\u002Fblog\u002Fai-dubbing-in-your-own-voice",{"slug":23,"title":24,"description":25,"date":26,"updated":26,"tags":27,"image":30,"url":31,"published_at":32},"one-newspaper-page-four-ocr-tools","Tried OCR on an old newspaper? Compare this page","One dense 1850 newspaper page, four OCR tools: one nearly right, one fluent but wrong. See the results, then run your own page.","2026-10-20",[28,29],"ocr","text extraction","https:\u002F\u002Fcontent.presentr.me\u002Fanalyze\u002Fassets\u002Fog.088293acda.png","https:\u002F\u002Fanalyze.presentr.me\u002Fblog\u002Fone-newspaper-page-four-ocr-tools","2026-10-20T20:50:29.423Z",{"slug":34,"title":35,"description":36,"date":37,"updated":38,"tags":39,"image":41,"url":42,"published_at":43},"fix-progressive-subtitle-drift","Subtitles Offset or Slowly Drifting? Diagnose the Difference","Check subtitle sync at the beginning, middle, and end to distinguish a constant offset, progressive drift, or a re-edited video.","2026-10-19","2026-10-23",[11,40],"captions","https:\u002F\u002Fcontent.presentr.me\u002Fanalyze\u002Fassets\u002Fog.743e8292aa.png","https:\u002F\u002Fanalyze.presentr.me\u002Fblog\u002Ffix-progressive-subtitle-drift","2026-10-19T19:30:48.590Z",{"slug":45,"title":46,"description":47,"date":48,"updated":48,"tags":49,"image":50,"url":51,"published_at":52},"subtitle-file-out-of-sync","A subtitle file can look valid and still be out of sync","A subtitle file 2.5 seconds late scored the same as the in-sync one on our own check. Why a text check cannot see sync, and what the audio shows.","2026-10-15",[11,40,10],"https:\u002F\u002Fcontent.presentr.me\u002Fanalyze\u002Fassets\u002Fog.f3a05ee827.png","https:\u002F\u002Fanalyze.presentr.me\u002Fblog\u002Fsubtitle-file-out-of-sync","2026-10-15T15:51:57.159Z",{},1793309251357]