Make AI videos that speak English

A 5-second clip with a person speaking English, made in Typeshoot and transcribed back to check it, plus English voices for longer narration.

3 voices · updated 12 November 2026

A clip that speaks English

PromptA friendly barista behind a sunny café counter looks into the camera, smiles and says in English: “Good morning! The coffee is ready.” Natural café ambience, no music.

Gemini Omni Flash, 360p, 5 s · 30 credits

Heard back: “Good morning! The coffee is ready.”

How to make a English video

  1. Connect Typeshoot to Claude or ChatGPT.
  2. Describe the clip and write the spoken line in English, in quotes.
  3. Pick a model with native sound (Gemini Omni Flash is the one tested on this page), or let the advisor choose. Draft at 360p first.
  4. Add a separate English voiceover and captions if you need a longer narration.

English voices for your video

  • Sarah

    ElevenLabs v4 · soft, professional female · 2 credits

    Heard back: “Good morning. This voice was made in a few seconds, right from the chat.”

  • George

    ElevenLabs v4 · warm British male, storyteller · 2 credits

    Heard back: “Good morning. This voice was made in a few seconds, right from the chat.”

  • Calm Woman

    MiniMax Speech 2.8 HD · calm female · 2 credits

    Heard back: “Good morning. This voice was made in a few seconds, right from the chat.”

Frequently asked questions

Can AI video models speak English?

Yes. Models with native sound, like Gemini Omni Flash, can speak a line you write in English; the clip above was transcribed back to check it. For longer narration, add a English voiceover.

How much does a English AI video cost?

A 5-second draft at 360p on Gemini Omni Flash is 30 credits; the same at 720p is 85.

Other languages

Try it in your own chat

Typeshoot adds image, video, voice and editing tools to Claude, ChatGPT and other assistants. 100 free credits to start, no card needed.

Get 100 free credits