hexgrad: Kokoro 82M
1 provider live- 1 live provider
Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese) using 54 preset voices organized by language and gender. At 82M parameters, it is well-suited for multilingual TTS deployments where footprint and cost efficiency matter.
- Input
- $0.99
- per million characters
Providers
Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.| # | Provider | Input |
|---|---|---|
| 1 | Data policy not declared | $0.99/M characters |
Voices
54 voices. Send one as voice in a text-to-speech request; without one, the model's default voice speaks.
af_alloyaf_aoedeaf_bellaaf_heartaf_jessicaaf_koreaf_nicoleaf_novaaf_riveraf_sarahaf_skyam_adamam_echoam_ericam_fenriram_liamam_michaelam_onyxam_puckam_santabf_alicebf_emmabf_isabellabf_lilybm_danielbm_fablebm_georgebm_lewisef_doraem_alexem_santaff_siwishf_alphahf_betahm_omegahm_psiif_saraim_nicolajf_alphajf_gongitsunejf_nezumijf_tebukurojm_kumopf_dorapm_alexpm_santazf_xiaobeizf_xiaonizf_xiaoxiaozf_xiaoyizm_yunjianzm_yunxizm_yunxiazm_yunyang
Price history
No price changes since Oct 23, 2026.
- DeepInfra$0.99/M characters
Questions
How much does hexgrad: Kokoro 82M cost?
hexgrad: Kokoro 82M costs $0.99 per million characters at DeepInfra, the provider requests go to first.
Do providers train on my prompts?
Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.
Can I serve hexgrad: Kokoro 82M myself?
Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.
Call it
import os
import httpx
# To choose a voice, send "voice" with one of the IDs listed under Voices on the model page, or as
# supported_voices by GET https://api.llm.buzz/api/v1/models?output_modalities=speech; without it, the default voice of the model speaks.
reply = httpx.post(
"https://api.llm.buzz/api/v1/audio/speech",
headers={"Authorization": f"Bearer {os.environ['LLM_BUZZ_KEY']}"},
json={"model": "hexgrad/kokoro-82m", "input": "Your order has shipped.", "response_format": "mp3"},
timeout=60,
)
reply.raise_for_status()
with open("reply.mp3", "wb") as file:
file.write(reply.content)import fs from "node:fs";
// To choose a voice, send "voice" with one of the IDs listed under Voices on the model page, or as
// supported_voices by GET https://api.llm.buzz/api/v1/models?output_modalities=speech; without it, the default voice of the model speaks.
const reply = await fetch("https://api.llm.buzz/api/v1/audio/speech", {
method: "POST",
headers: { Authorization: `Bearer ${process.env.LLM_BUZZ_KEY}`, "Content-Type": "application/json" },
body: JSON.stringify({ model: "hexgrad/kokoro-82m", input: "Your order has shipped.", response_format: "mp3" }),
});
if (!reply.ok) throw new Error(await reply.text());
fs.writeFileSync("reply.mp3", Buffer.from(await reply.arrayBuffer()));# To choose a voice, send "voice" with one of the IDs listed under Voices on the model page, or as
# supported_voices by GET https://api.llm.buzz/api/v1/models?output_modalities=speech; without it, the default voice of the model speaks.
curl https://api.llm.buzz/api/v1/audio/speech \
-H "Authorization: Bearer $LLM_BUZZ_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "hexgrad/kokoro-82m", "input": "Your order has shipped.", "response_format": "mp3"}' \
-o reply.mp3Endpoints
POST /api/v1/audio/speechAuthentication
Send your llm.buzz key as a Bearer token: Authorization: Bearer $LLM_BUZZ_KEY. Create keys in the console. The same key calls every model; each request pays the price of the provider that answered it.
More in Authentication and the API reference.
README
Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. It converts text to speech across 8 languages (American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese) using 54 preset voices organized by language and gender. At 82M parameters, it is well-suited for multilingual TTS deployments where footprint and cost efficiency matter.
- Model ID
- hexgrad/kokoro-82m
- Takes
- Text
- Answers
- Speech
- Weights
- Closed
- On llm.buzz since
- Oct 23, 2026