kling-video-o3/standard/text-to-video
Generate cinematic 3-15s videos from text with optional sound.
HeyGen's Avatar V Text To Video turns a script and a public look into a lip-synced clip at $0.07 per second.
Trading a filmed presenter for a script-led performance suits marketers, trainers, and founders.
For developers, Avatar V on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Product Hosts | Lesson Intros | Founder Updates.
A portrait shows a face. The line you type has to become a performance. Avatar V times the mouth to that script and adds a small nod or a quieter hand when you ask.
| Advantage | What you get |
|---|---|
| Script-led speech | The mouth follows the words you submit. |
| A reusable look | One public person can carry a whole series of Avatar V clips. |
| Optional motion | A short note can request a nod. Skip it and the Avatar V line still leads. |
| One rate | 720p and 1080p share the same price per second. |
You pick a voice on this page. You do not upload a recording. Camera directions will not rebuild the Avatar V room, because the look already has its set.
On RunComfy, try a line in the model UI, then repeat the same look, voice, and script through the HTTP API.
avatar_id, voice_id, script, resolution, and optional motion_prompt.These are the only controls on this page.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
avatar_id* | Yes (*) | String | Elise | Eight public looks | Person on camera. |
voice_id* | Yes (*) | String | Match look | Match look, or eight voices | Voice for the script. |
script* | Yes (*) | String | Harbor market line | Up to 5000 characters | Words to speak. Length sets the clip. |
resolution | No | String | 1080p | 720p, 1080p | Frame size. Same per-second rate. |
motion_prompt | No | String | Empty | Short text | Optional nod or hand note. |
There is no duration slider. The spoken line sets the length.
Avatar V bills $0.07 per second of the finished clip. Both frame sizes use that rate.
| Clip length | Price |
|---|---|
| 5s | $0.35 |
| 10s | $0.70 |
| 20s | $1.40 |
| 30s | $2.10 |
A longer script costs more only because the video is longer. The look and the voice do not add a fee.
script. Do not describe the room there.Generate cinematic 3-15s videos from text with optional sound.
Turn written scenes into cinematic clips with optional native audio.
FLUX 3 Max Text To Video turns a prompt into a short clip.
Reshape a source clip from a text prompt with native audio.
Generate premium-quality videos from text prompts with Google Veo 3.
HappyHorse 1.0 Reference to Video fuses up to 9 reference images and a prompt into a coherent multi-character clip with stable identity.
Avatar V turns a written script and a public look into a lip-synced talking clip. The mouth follows the words you submit, and an optional motion note can ask for a nod or a quieter hand. It fits product hosts, lesson intros, and short founder updates.
Avatar V offers eight public looks, each with a paired voice, plus eight named public voices. Choose Match look to keep the voice that belongs to the selected person, or pick a named voice when you want a different read. You do not upload a recording on this page.
Avatar V accepts a script of up to 5000 characters, and the spoken line sets the length. There is no duration slider. A longer script costs more only because the finished video is longer.
No. Avatar V bills $0.07 per second of the finished clip at both 720p and 1080p. The look and the voice do not add a separate fee. Read the line once if you want a rough length before you generate.
Use the Avatar V motion note for one small gesture, such as a nod or an open hand. Opposite moods in the same note fight each other. Leave it empty when you only want the words spoken.
Avatar V needs a public look, a voice, and a script. Resolution is 720p or 1080p. The motion note is optional, and the script must stay within 5000 characters. These looks are not a title tool, so add captions afterward.
Yes. Prototype Avatar V in the Playground Web UI, then send the same look, voice, script, resolution, and optional motion note through the RunComfy API. The API uses the same model. It does not promise a fixed turnaround or unlimited concurrency.
Avatar V costs $0.07 per second of the finished video. A 10-second clip is $0.70 and a 30-second clip is $2.10. Generations consume usd credits, and new accounts typically start with a trial balance.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
