Google Veo with dialogue and sound
Write the scene and the line a character says: Google's Veo 3.1 Fast renders the picture, the voice and the sound around it together, at 720p or 1080p for the same rate.
Pay per render · exact credit total shown first · credits never expire
Input
Text, or first/last frames
Length
4–8s
Quality
720p · 1080p
Audio
Generated with video
Made with Veo 3.1 Fast
The clip is 8 seconds at 720p from Veo 3.1 Fast, with the sound the model generated. Tap to hear it. The prompt under each clip is the literal prompt that made it.
Prompt: A street-food cook at a busy night market flips sizzling skewers on a smoking grill, looks up at the camera and says with a grin: "Fresh off the fire. Who wants the first one?" Warm lantern light, handheld medium shot. Sound: sizzling grill, crowd chatter, and his voice.
Make one with Veo 3.1 FastVeo 3.1 Fast is Google's quick Veo 3.1 model, now in the TalkPix AI Video studio. Use it when a clip needs someone to speak — a host greeting the viewer, a line of dialogue, a product shout-out — with ambience and effects generated in the same pass. It renders 4, 6 or 8 seconds in 16:9 or 9:16 and costs 3 credits per second at 720p and at 1080p, so the sharper output costs nothing extra.
Put the words in quotes in the prompt and say who speaks them; the voice is generated with the picture.
4, 6 or 8 seconds in 9:16 for Reels, TikTok and Shorts, or 16:9 for YouTube and ads.
1080p costs the same 3 credits per second as 720p, so a final cut does not cost more than a draft.
Model comparison
All 8 options are visible in one TalkPix studio, so you can compare capability and price before generating.
| Model | Use cases | Length | Quality | From | Open |
|---|---|---|---|---|---|
| P-Video 2 Pro | Sharp, natural motion with generated sound, ready in about half a minute. | 5–15s | 480p, 720p | 1 cr/s | Details |
| Seedance 1.5 Pro | Fast, affordable clips with generated sound. | 4–12s | 480p, 720p, 1080p | 1 cr/s | Details |
| Seedance 2.0 Mini | Affordable native-audio motion for drafts and frequent posting. | 4–15s | 480p, 720p | 2 cr/s | Details |
| Seedance 2.0 | Advanced motion, prompt accuracy, native sound, and output up to 4K. | 4–15s | 480p, 720p, 1080p, 4K | 3 cr/s | Details |
| Seedance 2.5 | Best consistency for complex actions, identity, and longer final clips. | 4–30s | 480p, 720p | 4 cr/s | Details |
| MiniMax H3 | Reference-driven video up to 2K at the lowest 2K credit rate. Includes generated sound. | 4–15s | 720p, 2K | 3 cr/s | Details |
| Veo 3.1 FastCurrent | Google's Veo 3.1 Fast: spoken lines, sound effects and ambience generated with the picture, at 720p or 1080p for the same rate. | 4–8s | 720p, 1080p | 3 cr/s | Details |
| Kling 3.0 | Premium motion, consistency, multi-shot quality, and native sound. | 3–15s | 720p, 1080p, 4K | 5 cr/s | Details |
How it works
Describe what is said and what is heard; Veo 3.1 Fast generates the sound together with the video.
Start the clip from your own image, and optionally set the frame it should end on. The image is cropped to the 16:9 or 9:16 shape you pick.
3 credits per second at either quality: 12, 18 or 24 credits for a 4, 6 or 8 second clip, shown before the render starts.
Prompt example
A street-food cook at a busy night market flips sizzling skewers on a smoking grill, looks up at the camera and says with a grin: "Fresh off the fire. Who wants the first one?" Warm lantern light, handheld medium shot. Sound: sizzling grill, crowd chatter, and his voice.
Try this modelTransparent credits
720p
3 credits per second
5 seconds = 15 credits
1080p
3 credits per second
5 seconds = 15 credits
Model line-up and credit rates last updated October 11, 2026.
FAQ
Veo 3.1 Fast is the faster version of Google's Veo 3.1 video model. It turns a text prompt — or a first frame you upload — into a short clip with generated sound, including spoken dialogue.
It costs 3 credits per second at 720p and 3 at 1080p. An 8-second clip reserves 24 credits at either quality, and the exact total is shown before anything renders.
Yes. Write the line in quotes and say who speaks it, for example: the barista smiles and says "Your usual?". The voice, lip movement and the surrounding sound are generated with the video. Results vary, so keep lines short — about one sentence per 4 seconds.
4, 6 or 8 seconds. The model renders only those lengths, so the studio's length control snaps to them. For longer clips pick Seedance 2.5 (up to 30 seconds) or Kling 3.0 (up to 15).
Yes. Add a first frame, and optionally a last frame, in the studio. Veo 3.1 Fast renders 16:9 or 9:16, so the image is cropped to the shape you choose. Saved characters (identity references) are not available on this model.
Open the studio with this model selected. Review the exact credit total before any render starts.
Open Veo 3.1 Fast