Voice your text with a living voice — or create your own
HancVoice — an international AI voice studio: text-to-speech with living intonation, private user voices, reincarnation, and transcription — in one window. WAV/MP3 export, REST API, payment by Visa/Mastercard.
AI
Harry · Warm
A studio where the voice comes alive
Everything for voice-over, custom voices, reincarnation and transcription — in a single window. See how it looks from the inside.
Voice text with lifelike intonation
Paste your text, pick a voice, set the emotion and pace — and get clean WAV or MP3. Smart intonation places the accents and pauses by the meaning of each sentence.
- "How to read" panel: emphasis, pause, mood, stress
- Smart intonation, sentence by sentence
- Effects, equalizer, ambiences and "Remember take"
Welcome to HancVoice — the studio where your text comes alive in a lifelike voice. Choose a voice, set the intonation, add emotion and ambience — and get professional voice-over in seconds.
154 ready voices and your own
A voice catalog with filters by language, gender and style, and one-click preview — or create your own private voice from a short sample in a couple of minutes.
- Filters by language, gender and style
- One-click voice preview
- "Create your own voice" in a couple of minutes
Your own voice in a couple of minutes
Upload a short sample — 15–30 seconds of clean speech — and the neural network builds your private voice model. From there, voice any text in your own voice.
- 15–30 second sample: record with a mic or upload a file
- Private model — never used to train shared models
- The finished voice is instantly available in the editor and via API
A sound studio right in your browser
An 8-band equalizer, character effects and atmospheric ambiences — dial in the timbre and mood of your voice-over without third-party software.
- 8-band equalizer: from 80 Hz to 10.5 kHz
- Character effects: radio, podcast, cinema, robot
- Atmospheric ambiences: rain, café, sea
Transfer an actor's delivery to any voice
This is speech-to-speech: upload your own read with its intonation, pauses and emotion — and apply the timbre you choose. Dubbing and voice swaps without losing the performance.
- The original intonation, pauses and emotion are preserved
- Any system or your own voice as the timbre
- Dubbing, voice replacement, re-voicing
The actor's delivery stays the same — only the timbre of the voice changes.
Audio and video → text with timecodes
Transcription with timecodes and ready-made SRT / VTT subtitles. Speaker labeling, speaker names and a short meeting summary — from the Business plan.
- Timecodes and SRT / VTT subtitles
- Speaker separation — from Business
- Speaker names and summary — from Business
Hi, let's start the meeting — we have three topics today.
Yes, three items on the agenda. Let's start with the release.
Great. I'll note the decisions and send everyone the summary.
Listen to our AI voice-over
Voices with natural intonation for any task — from ads to audiobooks.
Female voice — British English (Scottish accent), for ads and announcements.
Male voice — British English (southern accent), for stories and audiobooks.
Female voice — American English, for audiobooks and courses.
Male voice — American English, for ads and announcements.
Male voice — Irish English, for presentations and business.
Male voice — American English, for voice-over and reviews.
Male voice — American English, for social media and youth content.
Female voice — British English (southern accent), for voice-over and reviews.
Female voice — British English (northern accent), for ads and announcements.
Female voice — American English, for voice-over and announcements.
Female voice — American English, for voice-over and announcements.
Male voice — British English (Scottish accent), for ads and social media.
More than synthesis — a sound studio in your browser
What ordinary TTS doesn't have: lifelike intonation, reincarnation, post-production and transcription — in a single window.
Smart intonation
The model places emotion, accents and pauses by the meaning of each sentence — not mechanically, word by word.
Reincarnation
Upload your own acted delivery — intonation, pauses, emotion — and apply any timbre. Speech-to-speech.
Smart text preparation
Expands numbers, dates and abbreviations to fit the content type — legal, medical, finance, prose, poetry.
Sound studio
An 8-band equalizer, a "clean up" neural denoiser, 12 atmospheric ambiences and character effects — post-production right in your browser.
Transcription
Audio and video → text with timecodes and SRT/VTT subtitles. Speaker names and summary — from the Business plan.
Lock the take
Like a generation? Lock it in and get the same result across a series of clips or book chapters.
Three paths for one voice
Voice with system voices, create your own, and save different sound variants — all in one account and plan.
Text voice-over
Paste text → choose a system or your own voice → get clean WAV/MP3 for publishing, editing or integration.
Your own voice
Record a short sample → create a private voice model → save delivery variants for different tasks.
Voice as an asset Soon
An author's voice, demo and card in the marketplace with access via moderation. The section opens with the first approved voices — you can already request early access.
Voice-over for anything
One tool covers the needs of creators, business and education.
Video & YouTube
Voice-over for clips, shorts and short videos — no narrator and no studio.
Audiobooks
Voice chapters, long texts and courses in a single voice with pronunciation control.
Podcasts
Voice episodes and jingles with a lively conversational delivery.
Education
Lectures, courses and training — text becomes an audio lesson.
Advertising
Energetic spots, announcements and audio banners for social media.
IVR & bots
Voice menus and answering systems with a professional timbre.
10 languages: Russian and international
Russian, English, German, French, Spanish, Italian, Portuguese, Chinese, Japanese and Korean — for content localization and business scenarios.
Character packages for your volume
Choose a plan for a creator, a team or a studio. Payment by Visa/Mastercard, with receipts and refunds.
Built for comfortable work
A clear editor, transparent pricing and data on servers in EU — all in one service. Below are verifiable facts about the features.
Our own engine
Synthesis on our own servers in EU — data is processed under GDPR.
Transparent pricing
Clear character packages, payment by Visa/Mastercard, receipts and refunds.
5 000 characters free
Try it without a card: the first characters are on us, then it's by your plan.
Commercial use
Export with no service audio logos; usage rights are set by your plan and the service rules.
REST API
Synthesis, your own voice and transcription by key — to integrate into products and bots.
Responsive support
Live support and documentation — with no language barrier.
Features and limits match the current plans and may be refined.
What our users say
Stories from creators, studios and education teams for whom voice has become a working tool.
Voice content in your own voice
Record a short sample — and create a private custom voice model for voicing content. Then save sound variants: narrator, podcast, audiobook or phone.
One custom voice — several working deliveries
Save settings on top of your base voice and pick a ready variant in the editor: no re-recording and no new model.
Narrator variant
A crisp delivery for presentations, ads, training clips and corporate video.
Podcast variant
A more conversational pace, soft intonation and processing for episodes, interviews and clips.
Audiobook or IVR
Unhurried reading, a phone line, a warm narrator or another saved preset.
Author voices — the next commercial layer
The Marketplace brings together author voice cards, demos, rights moderation and voice access. Sales and author revenue accounting are part of the product ecosystem, and automated author payouts launch as a separate stage.
Frequently asked questions
Plans start from 4,90 € per month. You can pay per character with no subscription. The first 5 000 characters are free, with no card required.
The editor offers WAV export, while project export supports WAV and MP3. Over the API the main response format is WAV.
Yes, for commercial projects within your chosen plan, your rights to the source text and the service rules. Exports contain no HancVoice audio logos.
Fully. The model is trained on Cyrillic and places stress by meaning. Tricky cases can be corrected by hand in the editor.
Yes, the REST API is available on the Pro plan and above. Documentation, keys and request examples are in your dashboard.
Yes. On the Starter plan and above you can create a custom voice: record a sample — and voice texts in your own voice.
In the "Create voice" wizard you record a sample with a mic or upload audio/video, confirm your rights — and the voice is ready in a couple of minutes. Samples are stored in EU (GDPR), are never used to train shared models and are deleted together with the voice.
The marketplace is getting ready to launch. It's an ecosystem of author voices: cards, demos, rights moderation and voice access. At launch, author payouts are handled by manual request; automated author payouts are planned as a separate stage.
Voice your text right now
The first 5 000 characters are free. No card, no subscription.