Voice · hexgrad (open source)

Kokoro

A small open-source voice model, private and by far the cheapest. Sub Rosa uses it by default for narration.

Private Low cost
Latest versionKokoro v1.0January 27, 2025
Artificial Analysis Speech Arena1,064 Elo#10 of 10 on Artificial Analysis Speech Arena
Price$0.00157 per 1,000 characters$0.00472 a page read aloud
Key spec8 languages, 54 voices

What sets it apart

Kokoro is an 82-million-parameter open-weights model that runs on modest hardware, which is why it is the cheapest voice in the catalog and can run in private mode. It trades some expressiveness for speed and cost.

  • 82M parameters, Apache 2.0
  • 54 voices, 8 languages in v1.0
  • Trained for about $1,000 of GPU time

Recommended for: read a note or narrate a film.

Strengths and limits

Where it shines

  • Cheapest voice in the catalog by a wide margin
  • Private mode: nothing is kept
  • 54 voices across 8 languages

Think twice when

  • Only one French voice (ff_siwis)
  • Less expressive than the larger models
  • 54 voices
  • Up to 5,000 characters per request in Sub Rosa

Use cases

Long article read aloud

Read this blog post aloud in a calm, neutral voice so I can listen while I cook.

A very low cost per character keeps long texts affordable.

Private narration of sensitive notes

Read my meeting summary aloud.

Private mode means nothing is kept.

Against its rivals

  • Orpheus TTSOrpheus is more expressive in English but costs more and speaks English only.
  • Qwen3 TTSQwen3 TTS covers 10 languages with cloning, at several times Kokoro's price.
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. Kokoro v0.19Earlier, not in Sub Rosa
    • Initial release: English only, 10 voices, trained on under 100 hours of audio
    Source : huggingface.co
  2. Kokoro v1.0Latest
    • Multilingual: 8 languages instead of 1
    • 54 voices instead of 10, trained on a few hundred hours of audio
    Source : huggingface.co

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis Speech Arena: #10 of 10 models measured in the catalog. People listen to the same sentence read by two voices, without knowing the models, and pick the more natural one. An Elo rating: higher sounds more natural to more people. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Speech ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. ElevenLabs TTS v4 TurboElevenLabs1,330
  2. 2. ElevenLabs TTS v4ElevenLabs1,329
  3. 3. Gemini 3.1 Flash TTSGemini 3.1 Flash TTS1,209
  4. 4. ElevenLabs TTS v3ElevenLabs1,178
  5. 5. Gradium TTSGradium TTS1,151
  6. 6. MiniMax Speech-02 HDMiniMax Speech-02 HD1,114
  7. 7. Chatterbox HD (Resemble AI)Chatterbox HD1,102
  8. 8. ElevenLabs Turbo v2.5ElevenLabs1,097
  9. 9. ElevenLabs Multilingual v2ElevenLabs1,095
  10. 10. Kokoro Text to SpeechKokoro1,064
See the numbers
ModelElo
1. ElevenLabs TTS v4 Turbo1,330
2. ElevenLabs TTS v41,329
3. Gemini 3.1 Flash TTS1,209
4. ElevenLabs TTS v31,178
5. Gradium TTS1,151
6. MiniMax Speech-02 HD1,114
7. Chatterbox HD (Resemble AI)1,102
8. ElevenLabs Turbo v2.51,097
9. ElevenLabs Multilingual v21,095
10. Kokoro Text to Speech1,064

The model in this family

ModelUsePrivacyPrice
Kokoro Text to Speechtts-kokoroVoicePrivate$0.00157 per 1,000 characters$0.00472 a page read aloud

Specifications

SpecificationKokoro v1.0
ReleasedJanuary 27, 2025
Parameters82M
WeightsOpen, Apache 2.0
Acceptstext
Producesaudio
Languages8 languages, 54 voices
Price$0.00157 per 1,000 characters
PrivacyPrivate

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.

Sources

Everything on this page comes from these pages, read on October 16, 2026 or as dated on each score.

Show the 3 sources
Learn more about Kokoro ↗