Meet HeyGen Voice, the world’s best voice model and the first built to adapt to video. It delivers your script in your voice, with your pacing and expression, while adapting to the scene’s acoustics.
All HeyGen Voice needs is a 60-second phone recording to learn your timbre, accent, and phrasing. From there, it looks at the scene and figures out how you’d deliver the line as if you were really standing there.
1. Record your voice
2. HeyGen Voice
3. Speech for every scene
1. Record your voice
Original recording
Everyday room
2. HeyGen Voice
HeyGen Voice
3. Speech for every scene
Expressiveness Boost is a separate layer trained on what listeners prefer and scored against your reference the whole way, so it adds emphasis, rhythm, and inflection while staying unmistakably you. It is one slider from your baseline delivery to full energy, and zero gives you the base model back.
Expressiveness Boost · Off
The baseline delivery
A vision encoder and two scene captions tell the model the room, the mic distance, and the delivery the picture calls for. Across 50 environments from cathedral to beach, reviewers in our research judged its ambient sound a better fit than ElevenLabs v4, Cartesia Sonic 3.6, or Seedance 2.5.
Every voice model says it sounds the most realistic. We’d rather show you the data.
Read the technical reportIn the HeyGen app, thousands of people recorded a short voice sample. They heard the same script generated by HeyGen Voice, ElevenLabs v4, and Cartesia Sonic 3.6, unlabeled and in random order, and picked the one to use as their own.
See the dataChosen as their own voice
Three-way test · 6,153 votes
62.2%
Head-to-head vs ElevenLabs v4 · 8,332 votes
54.1%
Head-to-head vs Cartesia Sonic 3.6 · 7,286 votes
We also asked testers on Podonos which voices they would choose to narrate an entire lesson across 245 scripts in English, Spanish, German, French, and Chinese, 42,875 ratings in all. They chose HeyGen Voice over ElevenLabs v4 in 61.5% of decided votes, over Inworld TTS-2 in 68.1%, and over Cartesia Sonic 3.6 in 77.9%. It also led every system in clarity and native accent.
See the dataChosen to narrate a full lesson
HeyGen Voice’s share of decided votes
Share of decided narrator-choice votes, 245 cases, five languages, Holm-corrected p < 0.05.
A voice can sound exactly like you and still sound wrong for the shot. So we put the same voice in 50 places, including a podcast booth, cathedral, beach, and factory floor. We asked reviewers one blind question: does the sound match the picture? It did. Reviewers chose HeyGen Voice over Cartesia Sonic 3.6 in 73.3% of votes, over ElevenLabs v4 in 69.7%, and over Seedance 2.5 in 65.3%.
See the dataSound matches the picture
HeyGen Voice’s share of decided votes on ambient fit
Share of decided votes on ambient sound fit, 50 scenes × 5 reviewers, blind side-by-side video, Holm-corrected p < 0.05.
Listen to how the voice fits an open shoreline, with the sea stretching out behind the speaker.
Same script and reference voice within each scene. HeyGen Voice also receives the scene image.
HeyGen Voice wins 63% of voice-similarity votes against ElevenLabs v4 and ties Cartesia Sonic 3.6 at the top of the similarity scale.
Voice Clone fits delivery and adapt to the script, and Full Clone preserves the session you recorded. The two cover ranges that each competing model occupies at a single point.
HeyGen Voice: Two modes
Other models: One point each
Scene Mode leads on narrator choice. Exact Mode leads on sounding like your recording. Other models sit at a single point.
The same recording reads Spanish, German, French, or Chinese with a native accent. In cross-language cases, listeners chose HeyGen Voice as narrator over Cartesia Sonic 3.6 in 77.4% of decided votes.
Similarity parameter is a scale between "Adapts to scene" and "Sounds exactly like you". In the product it's a scale from 1 to 4 for you to customize.
Upload up to 60 seconds of audio from any device and HeyGen Voice keeps the person and drops the phone.
Give HeyGen Voice 30 minutes to two hours of your recordings, and it learns the finer details, like how your accent moves across words.
Pitch variation, background level, and ambient steadiness are each a slider, so the same scene can play nearly clean or clearly busy.
HeyGen App
Free
HeyGen Voice is included in every HeyGen video at no extra cost.
Get startedHeyGen PVC
$29/mo$99/mo
The Professional Voice Clone add-on trains on up to two hours of your voice so that every inflection, pause, and quirk comes with you.
Get startedAPI
$30per 1M characters
No packages, no minimums, no tiers. Pay for what you generate.
View docsGenerate speech from your professional voice clone with one REST request, or stream audio as it’s generated.
REST and streaming endpoints with SDKs for [Python, Node, and others].
import osimport requestsresponse = requests.post( "https://api.heygen.com/v3/models/audio/tts", headers={"X-Api-Key": os.environ["HEYGEN_API_KEY"]}, json={ "voice_id": "your_professional_voice_id", "text": "Welcome back. Today we're recording from the studio.", "language": "en", "seed": 7, },)response.raise_for_status()audio_url = response.json()["data"]["audio_url"]with open("studio.wav", "wb") as f: f.write(requests.get(audio_url).content)
Meet HeyGen Voice, the world’s best voice model and the first built to adapt to video.
Keeps your voice
HeyGen Voice: Two modes
Other models: One point each
Set a seed to keep delivery consistent across renders