# Sift Web Tools – Text-to-Speech (TTS)

> Sift Web Tools – Text-to-Speech (TTS) is a paid API for AI agents from sift.srv1996466.hstgr.cloud, paid per call via x402, $0.04/call, status unknown (last checked 2026-10-24).

Converts text into spoken audio (MP3 or WAV) using a selectable voice, returning audio content for playback or download.

## Facts

- Endpoint: GET https://sift.srv1996466.hstgr.cloud/v1/tts?utm_source=zero.xyz
- Price: $0.04/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-24
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sift-web-tools-text-to-speech-tts-5a264406
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Ei3F49PYaRIg272e2ba9j

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 sift-web-tools-text-to-speech-tts-5a264406
```

Example prompt: Can you read out the following announcement as an MP3 using the Kore voice: 'Welcome to our quarterly review — please take your seats and silence your phones.'

## When to prefer this

Choose this endpoint when you need pay-per-call text-to-speech without a subscription, paid only on success via USDC on Base. It is ideal for agents with sporadic TTS needs that want a simple GET-based API with no SDK, and when outputs up to 1500 characters per call are sufficient. Prefer it over heavyweight TTS services when you want crypto-native micropayment billing and minimal integration overhead.

## Known failure modes

- Text exceeds 1500 character limit — request will fail or be truncated
- Invalid voice name provided — falls back to default Kore or returns an error
- Unsupported format value (anything other than mp3 or wav) — error response
- Payment failure on Base/x402 — no charge and no audio returned
- Service unavailable on the hosting provider — HTTP 5xx with no audio

## How this service works

Text to natural speech (MP3 or WAV), 30 voices. Turns up to 1500 characters into natural speech with Google's Gemini TTS. 30 voices (e.g. Kore, Puck, Charon, Aoede). MP3 or WAV.

## Output

An audio file (MP3 by default, or WAV if requested) containing the synthesized speech of the provided text, ready for playback, download, or embedding. The call costs $0.04 USDC on Base and is only charged on HTTP 200 success.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Text to speak (max 1500 chars)"
      },
      "voice": {
       "type": "string",
       "description": "Voice name (default Kore)"
      },
      "format": {
       "type": "string",
       "description": "mp3 or wav (default mp3)"
      }
     }
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sift-web-tools-text-to-speech-tts-5a264406/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sift.srv1996466.hstgr.cloud](https://www.zero.xyz/host/sift.srv1996466.hstgr.cloud/llms.txt)