# BlockRun Text-to-Speech API

> BlockRun Text-to-Speech API is a paid API for AI agents from blockrun.ai, paid per call via x402, $0.003413/call, status unknown (last checked 2026-09-14, last successful call 2026-06-19).

Converts text to speech audio using ElevenLabs models, paid per-call in USDC with no API key required

## Facts

- Endpoint: POST https://blockrun.ai/api/v1/audio/speech
- Price: $0.003413/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Last successful call: 2026-06-19
- Success rate: 33% of calls made through Zero
- Rating: 2.7 / 5 from 2 reviews
- Activations on Zero: 7
- Tags: x402
- Canonical page: https://www.zero.xyz/c/blockrun-text-to-speech-api-6415afa4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_T7e4o7DCHlRQbzq3yfJS5

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 blockrun-text-to-speech-api-6415afa4 -d '<json body>'
```

Example prompt: Can you convert this text to speech using the ElevenLabs flash-v2.5 model with a female voice at normal speed and give me an mp3: 'Welcome to our platform, we're glad you're here.'

## When to prefer this

Choose this endpoint when you need on-demand text-to-speech with no API key setup, billed per call in USDC on Base or Solana. Ideal for agents or workflows that require infrequent or variable-volume speech synthesis without committing to a subscription, or when operating in a crypto-native payment environment using x402.

## Known failure modes

- Invalid or unsupported model ID returns an error
- Unrecognized voice alias or voice_id returns a 400 error
- Speed value outside 0.7–1.2 range is rejected
- Insufficient USDC balance causes payment failure and 402 response
- Empty or missing input text returns a validation error
- Unsupported response_format value causes a format error

## How this service works

Pay for the outcome. One endpoint for every model, tool and data source an agent needs — each call priced before it runs, at the best value per dollar. 103 models and 100 data and tool APIs.

## Output

An audio file (mp3 by default, or opus/pcm/wav if specified) containing the synthesized speech of the provided text, using the selected ElevenLabs voice and model, delivered as a binary audio response

## 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 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/blockrun-text-to-speech-api-6415afa4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from blockrun.ai](https://www.zero.xyz/host/blockrun.ai/llms.txt)