jaaari/kokoro-82m

Kokoro v1.0 - text-to-speech (82M params, based on StyleTTS2)

Capabilities

No capability data available

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`text` *	string	Text input (long text is automatically split)	`—`	—
`speed`	number	Speech speed multiplier (0.5 = half speed, 2.0 = double speed)	`1`	min: 0.1, max: 5
`voice`	string	Voice to use for synthesis	`"af_bella"`	af_alloy af_aoede af_bella af_jessica af_kore af_nicole af_nova af_river af_sarah af_sky am_adam am_echo am_eric am_fenrir am_liam am_michael am_onyx am_puck bf_alice bf_emma bf_isabella bf_lily bm_daniel bm_fable bm_george bm_lewis ff_siwis hf_alpha hf_beta hm_omega hm_psi if_sara im_nicola jf_alpha jf_gongitsune jf_nezumi jf_tebukuro jm_kumo zf_xiaobei zf_xiaoni zf_xiaoxiao zf_xiaoyi zm_yunjian zm_yunxi zm_yunxia zm_yunyang

text required string

Text input (long text is automatically split)

speed number

Speech speed multiplier (0.5 = half speed, 2.0 = double speed)

Default: 1 min: 0.1, max: 5

voice string

Voice to use for synthesis

Default: "af_bella"

af_alloy af_aoede af_bella af_jessica af_kore af_nicole af_nova af_river af_sarah af_sky am_adam am_echo am_eric am_fenrir am_liam am_michael am_onyx am_puck bf_alice bf_emma bf_isabella bf_lily bm_daniel bm_fable bm_george bm_lewis ff_siwis hf_alpha hf_beta hm_omega hm_psi if_sara im_nicola jf_alpha jf_gongitsune jf_nezumi jf_tebukuro jm_kumo zf_xiaobei zf_xiaoni zf_xiaoxiao zf_xiaoyi zm_yunjian zm_yunxi zm_yunxia zm_yunyang

Version: f559560eb822 Updated: 2/26/2026 80.0M runs