We combined 3 public TTS leaderboards into one meta-ranking of 110 models
Summary
A new meta-ranking combines three public TTS leaderboards into one unified ranking of 110 models across 46 providers, updated weekly with a fixed methodology.
Similar Articles
Text-to-Speech (TTS) Benchmark Revamped with Objective Standards and Blind Voting (46 models and counting)
A revamped TTS benchmark introduces objective standards and live blind voting to create an ELO rating for 46+ models, with participation open to the community.
@realmrfakename: TTS Arena is live. A blind benchmark for text-to-speech, rebuilt from the ground up - listen to two anonymous models, p…
TTS Arena launches as a blind benchmark for text-to-speech models, where users compare anonymous TTS outputs and vote for the more human-sounding one, updating a live leaderboard.
Some models got priced the same for a week, so I watched what people actually used
When several AI models were priced equally for a week, actual token usage revealed preference differences from leaderboard rankings, showing that coding and general chat have different top models and long context usage concentrated on two trusted models.
TTS Benchmark Comparison (all known TTS up until May 2026)
A user-created benchmark for comparing local TTS tools, with results for Windows and Mac, and Linux testing pending. Includes an HTML results page and GitHub repository.
I built a live ranking of every AI agent and foundation model (open source)
A developer launched AgentTape, a live ranking site that aggregates data from multiple sources (GitHub, Hugging Face, OpenRouter, etc.) to score and compare public AI agents and foundation models, aiming to provide a more holistic evaluation beyond benchmarks.