dreamina-3-0/pro/text-to-video
Turn text into detailed cinematic scenes with Dreamina 3.0 precision.
HeyGen's HeyGen Voice Text To Audio reads your paragraph as a 44.1 kHz WAV at $13.50 per million characters.
Trading a booked booth for an instant spoken read suits editors, teachers, and support teams.
For developers, HeyGen Voice 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: Narration Tracks | Lesson Audio | IVR Lines.
A booth read takes a booking. This page speaks the paragraph you paste and returns one 44.1 kHz WAV from a public voice you can pick before you commit.
| Advantage | What you get |
|---|---|
| A finished file | HeyGen Voice returns one WAV. You do not poll a job. |
| Public voices | HeyGen Voice offers eight English voices, from calm to bright. |
| Language control | Set a code, or leave Auto and let the text decide. |
| A tone slider | Expressiveness runs from 0 to 1. |
You do not upload a sample. Clones from another workspace are outside this HeyGen Voice page.
On RunComfy, listen in the model UI, then send the same text and voice through the HTTP API.
text, voice_id, optional language, and optional expressiveness_boost.These are the controls on this page.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
text* | Yes (*) | String | Harbor line | 1–5000 characters | Plain prose to speak. |
voice_id* | Yes (*) | String | Nadine - Calm & Gentle | Eight public voices | Voice that reads the text. |
language | No | String | auto | auto, en, es, fr, de, pt, it | Language of the text. Auto detects it. |
expressiveness_boost | No | Number | 0.8 | 0–1 | How lifted the delivery is. |
There is no duration slider. The paragraph sets the length.
HeyGen Voice bills $13.50 per 1,000,000 characters you submit. There is no per-request minimum. Spaces and punctuation count.
| Characters | Price |
|---|---|
| 200 | $0.0027 |
| 1,000 | $0.0135 |
| 5,000 | $0.0675 |
A longer paragraph costs more. The voice you pick does not change the rate.
text as prose. Parentheticals may be spoken too.Turn text into detailed cinematic scenes with Dreamina 3.0 precision.
Generate videos from text prompts with audio using Wan 2.5 Preview.
Enhanced 1080p image motion conversion for expressive, fluid video creation
Create lifelike cinematic video clips from prompts with motion control.
Open-weights image-to-video with optional last frame and native stereo audio.
Create lifelike videos from voices with accurate sync and adaptive dubbing.
HeyGen Voice reads the paragraph you paste in a public voice and returns one 44.1 kHz WAV. The request finishes on the create call, so you do not poll a job. It fits narration, lesson audio, and short phone prompts.
HeyGen Voice lists eight public English voices, from calm to bright. Language can stay on Auto, or you can set en, es, fr, de, pt, or it. You do not upload a voice sample on this page.
HeyGen Voice expressiveness runs from 0 to 1, and the default is 0.8. Lower values sit flatter. Higher values lift the delivery. Start near 0.5 if a bright voice feels performed.
HeyGen Voice accepts 1 to 5000 characters. Spaces and punctuation count. There is no duration slider, because the paragraph sets the length of the WAV.
HeyGen Voice needs plain text and one of the eight public voices. Language and expressiveness are optional. Spell unusual names the way they should sound, and replay dates and prices after the first take.
Yes. Listen to HeyGen Voice in the Playground Web UI, then send the same text, voice, language, and expressiveness through the RunComfy API. The API returns the same kind of WAV. It does not promise a fixed turnaround or unlimited concurrency.
HeyGen Voice costs $13.50 per 1,000,000 characters you submit. There is no per-request minimum. One thousand characters cost $0.0135, and the voice you pick does not change the rate. Generations consume usd credits.
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.
