Photo to Talking Video

One photo of a person and a voice. Type what they say or upload a recording, and the photo speaks it: lips, face and body moving with the sound.

See examples
Lena, a potter
  • A bike mechanic
    A bike mechanic
  • Carmen, in Spanish
    Carmen, in Spanish

One Photo, Then It Talks

  • Lena, a potterA typed script, voice Sarah · OmniHuman v2 · 16 s
  • A bike mechanicA typed script, voice George · OmniHuman v2 · 15 s
  • Carmen, in SpanishA typed script in Spanish, voice Laura · OmniHuman v2 · 15 s
01 · The voice

Type it, or upload it.

Upload an .mp3 or .wav of the words, or type a script and pick one of 21 voices. A typed script is read aloud first, as its own small step, so you hear the voice and know the clip's exact length before anything else is made.

  • Delivery tags like [laughs] or [whispers] go in the script.
  • A voice preview starts at 10 credits.
02 · The photo

The photo speaks.

OmniHuman v2 animates the person to the sound: the lips follow the words, and the face, head and hands move with how they are said. It sings as well as it speaks. A line of direction can set the scene, the movement and the camera.

  • A clear photo of one person, from the chest up or wider, works best.
  • The clip is as long as the voice: 4 seconds and up, to 30 seconds on Standard, 60 seconds on Pro, 120 seconds on Max.
03 · After

Then finish the clip.

The clip lands in your Library like any render. Upscale it, give it a new shape for another platform, cut it into a longer video in the editor, or export it as an MP4.

What a Talking Photo Does

  • 01

    Script to speech

    Type the words and pick a voice. The script is read aloud before the clip, so a wrong word costs a preview, not a video.

  • 02

    Your own recording

    Upload a voiceover, a podcast clip or a song as an .mp3 or .wav, and the photo is animated to it.

  • 03

    Lips that match

    The mouth is driven by the sound itself, so the words land on the lips at the right moment.

  • 04

    More than a mouth

    Head turns, expressions and hand gestures follow the voice, so the person reads as speaking, not a moving cut-out.

  • 05

    Direct the shot

    An optional line sets the scene, the movement and the camera: a slow push in, a nod at the end, a laugh.

  • 06

    As long as the voice

    From 4 seconds up to 120 on the Studio plan. The clip runs exactly the length of the audio.

  • 07

    Priced before it runs

    The voice is measured first, and the card shows the credits for that length. Nothing is spent until you approve it.

  • 08

    Your own photos

    Use a photo you upload, a still you made in the studio, or one of your saved elements.

  • 09

    Keeps going after

    Upscale the clip, reframe it to 9:16 or 16:9, or cut it with other clips in the editor.

How to make a photo talk

  • 1. Pick the photo

    Sign in and choose a photo of one person: an upload, a still you made, or an element. Confirm it is you, or that the person agreed.

  • 2. Add the voice

    Upload an .mp3 or .wav, or type the script, pick a voice and listen to the preview.

  • 3. Approve and render

    The card shows the credits for the voice's length. Approve it, and the clip lands in your Library.

Talking Photo Pricing

A talking photo is priced by the length of its voice, per second, rounded up to the whole second. The card shows the exact credits for your voice before anything renders.

ClipCredits
10-second clip252
30-second clip756
60-second clip1,512
120-second clip3,024
  • The longest voice per clip is 30 seconds on Standard, 60 seconds on Pro, 120 seconds on Max.
  • A typed script's voice preview is priced by its length, from 10 credits. An uploaded recording costs nothing extra.
  • The plans grant 1,500 credits a month on Standard, 3,500 credits a month on Pro, 9,500 credits a month on Max. A new workspace starts with 100 free credits.
See the plans

The Models Behind It

  • OmniHuman v2

    ByteDance's model for a person in a photo speaking or singing to a voice track. It draws the clip.

  • ElevenLabs v3

    Reads a typed script aloud in the voice you pick, with delivery tags for laughs, whispers and pauses.

  • Any video model, after

    The clip is a render like any other: finish it with an upscale or a reframe, or cut it beside clips from Kling, Veo or Seedance.

    See every model

FAQs about Talking Photos

One photo, one voice

Make a photo talk.

Type the words or upload them, hear the voice, then approve the clip at the price on the card.