# Seed Audio 1.0 Text-to-Speech (sol.blockrun.ai)

> Seed Audio 1.0 Text-to-Speech (sol.blockrun.ai) is a paid API for AI agents from sol.blockrun.ai, paid per call via x402, $0.004515/call, status unknown (last checked 2026-10-20).

Converts text into spoken audio using Seed Audio 1.0 TTS with configurable voice, speed, and output format

## Facts

- Endpoint: POST https://sol.blockrun.ai/api/v1/audio/speech?utm_source=zero.xyz
- Price: $0.004515/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/seed-audio-1-0-text-to-speech-sol-blockrun-ai-6a562535
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_kK5WIyBcCE5qFsEgBbhqM

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 seed-audio-1-0-text-to-speech-sol-blockrun-ai-6a562535 -d '<json body>'
```

Example prompt: Can you read this aloud and save it as an mp3 using the 'sarah' voice at normal speed: 'Welcome to our quarterly update. Here are the key highlights for this period.'

## When to prefer this

Choose this endpoint when you need pay-per-call text-to-speech synthesis with ElevenLabs-quality voices, configurable format and speed, no subscription required, and payment via USDC on Solana via the x402 protocol. Ideal for agents that need on-demand, low-latency voice generation without managing API keys or monthly plans.

## Known failure modes

- Invalid or unsupported voice alias returns an error
- Speed value outside 0.7–1.2 range may be rejected or clamped
- Empty or excessively long input text may fail
- Unsupported response_format value causes format error
- Payment of $0.085995 USDC must be completed via x402 or request is rejected
- Invalid model ID returns model-not-found error

## How this service works

ElevenLabs v3 text-to-speech

## Output

Returns a binary audio file in the requested format (mp3, opus, pcm, or wav) containing synthesized speech of the input text, rendered with the selected voice model and playback speed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "string",
   "description": "Text to synthesize into speech"
  },
  "model": {
   "type": "string",
   "description": "Speech model ID (e.g., elevenlabs/flash-v2.5)"
  },
  "speed": {
   "type": "number",
   "description": "Playback speed 0.7-1.2 (optional)"
  },
  "voice": {
   "type": "string",
   "description": "Voice alias (e.g., sarah, george) or raw ElevenLabs voice_id"
  },
  "response_format": {
   "type": "string",
   "description": "Audio format: mp3 (default), opus, pcm, wav"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/seed-audio-1-0-text-to-speech-sol-blockrun-ai-6a562535/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sol.blockrun.ai](https://www.zero.xyz/host/sol.blockrun.ai/llms.txt)