Transcription & Voice AI
AI audio transcription, voice cloning and text-to-speech
Turn your meetings, calls and audio or video files into text, then translate them, summarise them or have them read by an AI voice — your own, if you like.
- 10 free minutes
- No credit card
- No subscription

What you get
- Live transcription from the microphone
- Transcription from audio or video files
- Copy and download in one click
- Text-to-speech and voice cloning
- languages supported
- 13+
- max file size
- 500 Mo
- AI models
- 3
- transformation modes
- 4
Three tools, one app
Pick what you need: live, from a file, or to generate a voice.

Real time
Turn on the mic and follow the transcription while you speak.
Learn more : Live transcription

How it works
From voice to usable text in three steps.
Sign in
One click with Google, that's it.
Speak or upload
Live microphone or audio / video file.
Get the text
Copy, export, or translate in one click.
Advanced AI transcription and text-to-speech features
Voqia combines real-time transcription, text-to-speech, voice cloning, and AI transformation in a single intuitive interface.
Real-time transcription
Turn on your microphone or capture system audio for instant transcription. Text appears as you speak, supporting 13+ languages.
Audio and video file transcription
Upload your audio or video files (MP3, WAV, MP4, MOV and more) up to 500 MB. Transcription is generated in seconds with precise timestamps.
Instant AI translation
Translate your transcriptions in real time to any target language. Translation displays live alongside the original text.
Speaker separation (diarization)
Automatically identify different speakers in a recording. Rename each voice for a clear record of who said what.
AI automatic summary
Generate a concise, structured summary of your transcriptions with one click. Perfect for meeting minutes, lectures, and interviews.
4 AI transformation modes
Beyond transcription: translate, ask questions, improve text, or fact-check. Four transformation modes powered by Google Gemini.
Text-to-Speech (TTS)
Convert any text to natural, fluid speech. Choose from 9 languages and use your own cloned voice for personalized results.
AI Voice Cloning
Record a few seconds of your voice and create a realistic voice clone. Then use that voice to generate speech from any text.
Simple pricing, no subscription
Start for free, then buy minutes only when you need them. They never expire.
Free
0 €
- 10 min of transcription
- 1 voice clone
- No credit card required
Starter
4,99 € one-off
- 60 min of transcription
- 2 voice clones
- Valid for life
Popular
Pro
9,99 € one-off
- 180 min of transcription
- 4 voice clones
- -33% compared to Starter
Business
24,99 € one-off
- 600 min of transcription
- 10 voice clones
- -50% compared to Starter
One-off payment secured by Stripe · Minutes never expire · No automatic renewal
Transcription in 13+ languages
Voqia transcribes speech to text in over 13 languages, with automatic detection and an interface in French, English, and Arabic.
- Français
- English
- Español
- Deutsch
- Italiano
- Português
- Türkçe
- Русский
- العربية
The Voqia interface is available in French, English, and Arabic (with full RTL support).
Frequently asked questions about AI transcription
What is Voqia?
Voqia is a French AI audio transcription platform. It converts speech to text in real time or from audio/video files, powered by advanced AI.
How can I transcribe audio for free?
Create a free account with Google in one click. You get 10 free minutes of transcription, no credit card required. Choose live mode (microphone) or upload an audio file.
What languages does Voqia support?
Voqia supports 13+ transcription languages: French, English, Spanish, German, Italian, Portuguese, Arabic, Russian, Turkish, and more. The interface is available in French, English, and Arabic.
How does real-time transcription work?
Turn on your microphone or share your screen audio. Voqia captures the sound and transcribes it instantly using our advanced AI. Text appears live as you speak.
How much does Voqia cost?
Voqia is free to start with 10 minutes included. Paid plans start at 4.99 EUR for 1 hour, with no subscription. Purchased minutes are valid for life.
How to transcribe a meeting with Voqia?
Launch live mode, activate your microphone or system audio capture to record your Zoom, Teams, or Meet meeting. Transcription appears in real time. Export the text with one click.
What file formats are accepted?
Voqia accepts audio formats (MP3, WAV, M4A, AAC, OGG, FLAC, WebM) and video (MP4, MOV) up to 500 MB. Transcription includes precise timestamps for each segment.
Does speaker separation work with all models?
Diarization (speaker separation) is available with the advanced transcription model in file mode. It automatically identifies different speakers and lets you rename them.
What is text-to-speech on Voqia?
Voqia includes text-to-speech (TTS) powered by our advanced AI. Enter text, choose your cloned voice and a language, then generate natural, fluid audio in seconds.
How do I clone my voice with Voqia?
Go to the 'Clone my voice' tab on the Voice page. Read the displayed text aloud for at least 10 seconds, name your voice, then click 'Create my voice'. Your voice clone will be ready in moments.
How many voices can I clone?
The number of cloned voices depends on your plan: 1 voice for free accounts, 2 for Starter, 4 for Pro, and 10 for Business. TTS minutes are shared with transcription minutes.
What languages does text-to-speech support?
Voqia text-to-speech supports 9 languages: French, English, Spanish, Portuguese, Italian, Dutch, German, Hindi, and Arabic. Your cloned voice can generate speech in any of these languages.
Ready to turn your voice into text?
Create your account in one click with Google and get 10 free minutes, no credit card required.
Voqia is powered by advanced AI for accurate transcription, natural text-to-speech, and AI voice cloning. Transcribe, generate speech with your own voice, translate, and summarize — all in one platform.