As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/kokoro-82m/

# Kokoro-82M

hexgrad, Kokoro family. Status: current. Type: speech and audio. Released: 2025-01-27.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Hugging Face | `hexgrad/Kokoro-82M` |  | https://huggingface.co/hexgrad/Kokoro-82M |
| pip | `kokoro` |  | https://github.com/hexgrad/kokoro |
| DeepInfra | `hexgrad/Kokoro-82M` |  | https://deepinfra.com/hexgrad/Kokoro-82M |
| OpenRouter |  |  | https://openrouter.ai/hexgrad/kokoro-82m |

## Pricing

- Per 1M characters: $0.65
- Unit as published: USD per 1M characters (cheapest hosted price per Artificial Analysis); self-hosting free
- Source: https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice
- Last checked: 2026-09-29

## Specs

- Input: text
- Output: audio
- Context window: not published
- Max output: not published
- Open weights: yes
- Licence: apache-2.0

## Where it stands

- Newer speech and audio models in the registry since its release: 104. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Weights are public under a permissive licence (Apache-2.0).

## What stands out

- Tiny model, top-tier quality: 82M-param StyleTTS2 + ISTFTNet model trained for ~$1,000 (1,000 A100 h) on permissive data; v0.19 hit #1 on the HF TTS Spaces Arena; still top-5 open weights on Artificial Analysis (~1065 Elo) in Sept 2026. Source: https://huggingface.co/hexgrad/Kokoro-82M

## Notes

v1.0: 54 preset voices, 8 languages (US/UK English, Spanish, French, Hindi, Italian, Japanese, Brazilian Portuguese, Mandarin), 24 kHz. No voice cloning. v0.19 was 2024-12-25. ~11.5M HF downloads/month.

Sources: https://huggingface.co/hexgrad/Kokoro-82M , https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice

Model page: https://postcutoff.com/m/kokoro-82m/