# Text-to-Speech Lite (Kokoro-82M)

> Text-to-Speech Lite (Kokoro-82M) is a paid API for AI agents from agent402.tools, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Converts text to speech using the Kokoro-82M model at a low cost, returning base64-encoded MP3 or PCM audio

## Facts

- Endpoint: POST https://agent402.tools/api/tts-lite
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/text-to-speech-lite-kokoro-82m-fb4ed152
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_T73c0EEeqpSxV54nlgaF0

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability text-to-speech-lite-kokoro-82m-fb4ed152 -d '<json body>'
```

Example prompt: Convert this 200-character notification message to speech using the nova voice and return it as an MP3: 'Your order has shipped and will arrive by Friday. Thank you for shopping with us!'

## When to prefer this

Choose this endpoint when cost per call is the primary concern and you can tolerate a more synthetic-sounding voice. It is ten times cheaper than /api/tts and is best for high-volume use cases such as bulk narration, agent speech, or notification audio where premium voice timbre is not required. Use /api/tts or /api/tts-hd instead when voice naturalness matters more than cost.

## Known failure modes

- Text exceeds 2000 character limit — request rejected
- Invalid voice name supplied — may default or error
- Unsupported audio format requested — only mp3 and pcm supported on this endpoint
- Payment not provided or insufficient (x402 protocol) — 402 response
- OpenRouter upstream unavailability — 502 or timeout

## How this service works

Convert text to speech with Kokoro-82M, ten times cheaper than /api/tts. Returns base64-encoded mp3 or pcm. The same request shape and the same ten OpenAI voice names as /api/tts, mapped to Kokoro's own voices; the voice is synthetic-sounding where the OpenAI tiers are not, which is the whole trade. Use this for high-volume narration, notifications and agent speech where the cost per call matters more than the timbre; use /api/tts or /api/tts-hd when it does not.

## Output

A JSON object containing: base64-encoded audio data (MP3 or PCM), the character count of the input, the model used (hexgrad/kokoro-82m), the actual Kokoro voice name used, the audio format, and the provider (openrouter).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to convert to speech (max 2000 chars)"
  },
  "voice": {
   "type": "string",
   "description": "Voice: alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, shimmer (default: alloy) - mapped to the nearest Kokoro voice, which is named back in the response"
  },
  "format": {
   "type": "string",
   "description": "Audio format: mp3 or pcm (default: mp3). The other formats are on /api/tts"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "audio": "<base64-encoded audio>",
  "chars": 20,
  "model": "hexgrad/kokoro-82m",
  "voice": "af_alloy",
  "format": "mp3",
  "provider": "openrouter"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/text-to-speech-lite-kokoro-82m-fb4ed152/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent402.tools](https://www.zero.xyz/host/agent402.tools/llms.txt)