HeyGen Voice
HeyGen text-to-speech: 10 ready voices for videos, presentations and avatars
What it's the best tool for
- Suited for voice-over, presentations, and avatar lines
- 10 ready voices: Nadine, Tabitha, Noelle, Meredith, Sabrina, Bram, Gareth, Lucian, Weston, Vincent
- Up to 5,000 characters per request
- Export to MP3 and WAV
- Simple control: text and a voice, no extra settings
When to reach for something else
- No speed or tone settings
- Only the 10 ready voices are available
- Up to 5,000 characters per request
- This is voice-over only: video and avatars are assembled separately
How HeyGen Voice responds
HeyGen Voice
Four scenarios where it pays for itself
More about HeyGen Voice
HeyGen Voice Online — AI Voice for Video
HeyGen Voice is speech synthesis from HeyGen, the platform for AI-avatar video. The model suits voice-over in clips, presentation narration, and avatar lines. 10 ready voices and up to 5,000 characters per request, all in the browser on NetRoom.
Voice-over for video, presentations, and avatars
HeyGen Voice is aimed at video work: narration for ads and training clips, a presenter's voice for slides, lines for talking avatars. On NetRoom you get the voice itself as an audio file, and you assemble the video, slides, or avatar in the editor you prefer. The track is ready to go straight under the footage.
10 ready voices
The library has ten voices: Nadine, Tabitha, Noelle, Meredith, Sabrina, Bram, Gareth, Lucian, Weston, and Vincent. A voice is picked from the list, and a long script is read by the same narrator from start to finish, so a series of videos sounds consistent.
Simple control
The model has no separate speed or tone settings: you take the text, choose a voice, and get a finished track. That lowers the barrier, since there are no parameters to tune for each clip. If you need fine pacing, look at the other Sound models that offer a speed control.
Length and formats
One request voices up to 5,000 characters. The result downloads as MP3 or WAV. A script longer than the limit is easy to split by scene or slide and voice with the same voice.
Who it is for
Marketers get narration for ad clips. Teachers and trainers get a voice for courses and presentations. Channel owners and bloggers get video voice-over without a studio. Product teams get lines for avatars and demos.
How to voice a script
1. Sign up on NetRoom and top up your balance. 2. Open the Sound section and pick HeyGen Voice. 3. Paste the script and choose a voice. 4. Download the track as MP3 or WAV. No subscription: you pay for the voice-over you generate, and the current rate is shown on this page.
Another HeyGen model
If you want a lower-latency version at a more affordable price with the same ten voices, see HeyGen Voice Turbo.
Voice your first video — start on NetRoom.
What changed HeyGen Voice
- + Added voice model HeyGen Voice (HeyGen).
Use HeyGen Voice via the API
The same engine, straight from your code: one key and one balance for text, images, video and sound. Pay only for the requests you make.
curl https://netroom.ai/api/v1/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "heygen/heygen-voice-1", "input": {"prompt": "A cinematic mountain sunrise"}}'The model id is already in the example. The full parameter reference and prices live in GET /api/v1/models and in the docs.
Try HeyGen Voice
right now
Free access to basic models. No card, no obligations.