Revision History
Text-to-Speech · 7 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected benchmark figures that credited OpenAI's and Google's Labelbox scores to ElevenLabs, Amazon Polly and OpenAI TTS prices, the claim that Stephen Hawking used a DECtalk, the date WaveNet reached Google Assistant (2017, not 2018), WaveNet's original sample rate, an impossible CosyVoice 2 MOS of 5.53, market-size figures that did not match the cited report, and a false claim that Voxtral TTS was the first open-weight TTS from a major lab (plus 25 minor fixes)
Version 7 · Nov 1, 2026, 11:53 AM
- Cross-link Text-to-Speech Models catalogue
Version 6 · Oct 13, 2026, 09:15 AM
- Added 6 contextual internal links
Version 5 · Jul 23, 2026, 03:04 PM