Skip to main content
ModelSpeech & Audio AIvWaveNet 2024

Google WaveNet

by Google / DeepMind · paid · Last verified 2026-03-17

Google WaveNet is DeepMind's pioneering generative model for raw audio waveforms that dramatically advanced the state of the art in text-to-speech naturalness when published in 2016 and continues to power Google Assistant, Google Cloud TTS, and various Google products at massive scale. Its autoregressive waveform generation approach established the template for neural vocoder research and inspired a generation of TTS architectures.

https://cloud.google.com/text-to-speech
B+
B+Good
Adoption: B+Quality: AFreshness: B+Citations: A+Engagement: F

Specifications

License
Proprietary
Pricing
paid
Capabilities
text-to-speech, ssml-control, multilingual-tts, custom-voice, real-time-synthesis
Integrations
google-cloud-sdk, dialogflow, vertex-ai
Use Cases
google-assistant, ivr-systems, accessibility, content-narration, enterprise-applications
API Available
Yes
Parameters
Undisclosed
Context Window
N/A
Modalities
text, audio
Training Cutoff
2024
Tags
text-to-speech, wavenet, google, deep-mind, neural-tts
Added
2026-03-17
Completeness
100%

Index Score

70.5
Adoption
78
Quality
84
Freshness
75
Citations
90
Engagement
0

Explore the full AI ecosystem on Agents as a Service