# Deepgram Text-to-Speech (Aura-2) via Locus x402

> Deepgram Text-to-Speech (Aura-2) via Locus x402 is a paid API for AI agents from deepgram.x402.paywithlocus.com, paid per call via x402, $0.023/call, status unknown (last checked 2026-10-12).

Converts text into natural-sounding speech audio using Deepgram's Aura-2 TTS models, returning audio in configurable formats and encodings.

## Facts

- Endpoint: POST https://deepgram.x402.paywithlocus.com/deepgram/speak?utm_source=zero.xyz
- Price: $0.023/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/deepgram-text-to-speech-aura-2-via-locus-x402-9681436e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qT0fRAIjWmJcmkIyJ9SKa

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 deepgram-text-to-speech-aura-2-via-locus-x402-9681436e -d '<json body>'
```

Example prompt: Use Deepgram Aura-2 to read this aloud in the Thalia voice as an mp3: 'Welcome to our platform. We're glad you're here. Let's get started together.'

## When to prefer this

Choose this endpoint when you need high-quality, natural-sounding speech synthesis powered by Deepgram's Aura-2 models, especially when paying per-call via USDC x402 micropayments without API key management. Prefer over alternatives when you need flexible voice/encoding/format control (mp3, wav, flac, opus, etc.) and want Deepgram's production-grade TTS quality on a pay-as-you-go basis.

## Known failure modes

- Text exceeds recommended ~2000 character limit — may result in truncation or error
- Invalid model name format (must follow aura-2-{voice}-{lang}) — returns validation error
- Unsupported encoding/container combination — may return format error
- Insufficient USDC payment — payment rejected before processing
- Network timeout for long synthesis jobs — request may need retry via statusUrl

## How this service works

Industry-leading speech AI — transcribe audio from URLs with Nova-3, generate natural speech with Aura-2 TTS, and analyze text for sentiment, topics, intents, and summaries.

## Output

Returns a JSON object containing the generated audio data payload, payment confirmation details (settled and authorized USDC amounts), a unique request ID, a status URL for tracking, and a success flag. The audio content is embedded in the `data` field.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "model": {
   "type": "string"
  },
  "encoding": {
   "type": "string"
  },
  "container": {
   "type": "string"
  },
  "sample_rate": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "payment": {
   "scheme": "exact",
   "settledUsdc": "0.001000",
   "authorizedMaxUsdc": "0.001000"
  },
  "request": {
   "id": "00000000-0000-4000-8000-000000000000",
   "statusUrl": "/requests/00000000-0000-4000-8000-000000000000"
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/deepgram-text-to-speech-aura-2-via-locus-x402-9681436e/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from deepgram.x402.paywithlocus.com](https://www.zero.xyz/host/deepgram.x402.paywithlocus.com/llms.txt)