Language & Translation · Recorded milestone
Neural speech synthesis
Recorded year2016
DeepMind's WaveNet generates natural-sounding speech with neural networks, leading to today's voice cloning.
Explore this milestone on the interactive mapBuilt on
Led to
- Live voice translationRecorded · 2024enables
- AI music goes mainstreamRecorded · 2025enables
- Synthetic celebritiesRecorded · 2025enables
- Deepfake forensics in courtForecast · ~2027enables
- Universal real-time translationForecast · ~2027enables
- AI stand-ins at meetingsForecast · ~2028enables
- Automatic dubbing of all videoForecast · ~2028enables
- BCIs restore speech and movementForecast · ~2033enables
- Personal voice avatarsForecast · ~2035enables
Sources & evidence
Dataset updated 2026-10-18. This individual record has not been separately re-reviewed.