Kokoro 82M API
Kokoro 82M text to speech — the cheapest AI speech available, billed on input length.
The cheapest speech model on YepAPI by a wide margin — roughly 24× less per character than the mid-tier models — while still covering 8 languages with 54 named voices. Open weights, 82M parameters.
Takes 30 seconds.
Kokoro 82M API pricing
Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated August 6, 2026.
| Billing | Price |
|---|---|
| Rate | $0.0014/1K chars |
| What it costs | Per job |
|---|---|
| Short reply200 characters | $0.0003 |
| Blog post narration10,000 characters (~1,600 words) | $0.014 |
| Audiobook chapter100,000 characters | $0.14 |
4,900+
Developers
2.3M+
API calls served
184
Endpoints
$0.01
Per call
Yep, that's it.
Playground coming soon — use the API endpoint directly with your API key.
Kokoro 82M specs
| Provider | hexgrad |
|---|---|
| Model ID | hexgrad/kokoro-82m |
| Endpoint | /v1/media/queue |
| Type | Text to Speech |
| Output formats | mp3 |
| Voices | 15 presets (default af_bella) |
How to get a Kokoro 82M API key
- 1
Create an account
Sign up at yepapi.com with Google or email. It takes about 30 seconds.
- 2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
- 3
Call Kokoro 82M
Send a request to /v1/media/queue with the x-api-key header and model "hexgrad/kokoro-82m".
- 4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.
Strengths
At a fraction of a cent per thousand characters it is roughly 24× cheaper than the mid-tier models.
American and British English, Spanish, French, Hindi, Italian, Japanese, Portuguese, and Chinese.
Voices are prefixed by language and gender — `af_` American female, `bm_` British male, `jf_` Japanese female.
An open model you can evaluate and reason about, not a closed endpoint.
Quick start
Copy this snippet and start making calls with Kokoro 82M.
// Step 1: Submit job
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "hexgrad/kokoro-82m",
"prompt": "Every article on the site now has an audio version, generated automatically the moment it publishes.",
"options": {
"voice": "af_bella"
}
}),
});
const { data } = await res.json();
const jobId = data.jobId;
// Step 2: Poll for result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${jobId}`, {
headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status: "pending" | "processing" | "completed" | "failed"
// job.result: { text?, image?, audio?, video? }Kokoro 82M vs similar models
Every model below runs on the same API key — switch by changing the model ID.
| Model | Provider | Price |
|---|---|---|
| Kokoro 82M | hexgrad | $0.0014/1K chars |
| Fish Audio Drama 3 | Fish Audio | $0.0042/1K chars |
| HeyGen Voice Turbo | HeyGen | $0.0084/1K chars |
| Sesame CSM 1B | Sesame | $0.0148/1K chars |
| Voxtral TTS 3 | Mistral | $0.0302/1K chars |
| MAI-Voice-2.1 Flash | Microsoft | $0.0316/1K chars |
| HeyGen Voice | HeyGen | $0.0316/1K chars |
| MAI-Voice-2 Flash | Microsoft | $0.0317/1K chars |
Why use Kokoro 82M through YepAPI?
Kokoro 82M API — the cheapest AI text-to-speech
Kokoro 82M is a lightweight, open-weight text-to-speech model from hexgrad. At 82M parameters it is by far the cheapest speech model on YepAPI — roughly 24× cheaper per character than the mid-tier models — while still covering 8 languages with 54 named voices.
That price makes bulk narration viable: audio versions of every article, every product description, every changelog entry. Billed at $0.0014 per 1,000 characters.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
The cheapest speech model on YepAPI by a wide margin — roughly 24× less per character than the mid-tier models — while still covering 8 languages with 54 named voices. Open weights, 82M parameters.
Kokoro 82M costs $0.0014/1K chars through YepAPI, billed per request with no monthly fee. For example, a short reply (200 characters) costs about $0.0003.
Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Kokoro 82M and every other model — no separate hexgrad account or waitlist.
Use "hexgrad/kokoro-82m" as the model on /v1/media/queue. The short alias "kokoro" also works.
Explore more models
Eleven Flash v2.5
ElevenLabsEleven Flash v2.5 text to speech — ultra-low-latency speech in 32 languages, billed on input length.
Eleven v4
ElevenLabsEleven v4 text to speech — ElevenLabs' most expressive model, 90+ languages, billed on input length.
Fish Audio S2.1 Pro Free
Fish AudioFish Audio S2.1 Pro Free text to speech — free tier for prototyping, billed on input length.
Eleven v3
ElevenLabsEleven v3 text to speech — emotionally rich speech with audio tags, 70+ languages, billed on input length.
Gemini 3.8 Flash Lite TTS
GoogleGemini 3.8 Flash Lite TTS text to speech — fast, high-throughput Gemini 3.8 TTS, 30 voices, billed on input length.
Eleven Multilingual v2
ElevenLabsEleven Multilingual v2 text to speech — lifelike long-form narration in 29 languages, billed on input length.
More Text to Speech models
- Gemini 3.8 Flash TTS API · Google
- Eleven Flash v2 API · ElevenLabs
- Gemini 3.1 Flash TTS API · Google
- Fish Audio S2.1 Pro API · Fish Audio
- Orpheus 3B API · Canopy Labs
- MAI-Voice-2.1 API · Microsoft
- Deepgram Aura-2 API · Deepgram
- Sesame CSM 1B API · Sesame
- HeyGen Voice Turbo API · HeyGen
- Voxtral TTS 3 API · Mistral
- Eleven Turbo v2.5 API · ElevenLabs
- MiniMax Speech 2.8 HD API · MiniMax