Kokoro 82M
Compact open-weight text-to-speech model praised for quality at a tiny 82M parameter size.
Our editorial assessment, based on the public sources listed below. Last reviewed .
- Task rank
- #20
- Tier
- A
- Score
- 73.3
Strengths
- Very small 82M-parameter footprint
- Open weights for self-hosting
- Strong quality-to-size ratio
Considerations
- Fewer enterprise features than hosted platforms
- Requires technical setup to deploy
Price
Open weights / free
Shown for reference — price is not part of the score.
Score breakdown
- Performance
- 74.0
- 55% of score
- Reputation
- 68.0
- 35% of score
- Recency
- 88.0
- 10% of score
The overall score combines these sub-scores using the weights shown. How we score →
Verification status
Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.
- Pricing
- Benchmark
- Reputation
- Feature list
Checked against the sources listed below.
Sources
- Awesome Agents: best AI voice cloning tools 2026 (opens in a new tab)Accessed:
- BeFreed — Best TTS Models 2026 (opens in a new tab)Accessed:
- AIMojo: 11 best AI voice and TTS tools 2026 (opens in a new tab)Accessed:
- Best AI voice generators 2026 (opens in a new tab)Accessed:
- 10 best text to speech tools 2026 (opens in a new tab)Accessed:
Alternatives in Voice / TTS
- #1ElevenLabsSScore 96.4Voice generation platform with a 3,000+ voice library, cross-lingual cloning, and the expressive Eleven v3 model used widely for agents, dubbing, and long-form narration.
- #2CartesiaSScore 86.6Real-time voice agent TTS built on a state-space model, with Sonic 3 hitting roughly 40–90ms time-to-first-audio and 3-second voice cloning.
- #19TypecastAScore 74.0Voice studio built around expressive character voices and cloning for narrated content.