# HeyGen Speech (via OpenRouter)

> HeyGen Speech (via OpenRouter) is a paid API for AI agents from HeyGen at heygen.mpp.tempo.xyz, paid per call via MPP, price unknown, status unknown (last checked 2026-11-03).

Converts text to speech audio bytes using HeyGen's TTS models, billed per character or audio unit via a one-shot USDC payment.

## Facts

- Endpoint: POST https://heygen.mpp.tempo.xyz/v1/audio/speech?utm_source=zero.xyz
- Price: price unknown
- Payment: MPP
- Status: unknown
- Last checked: 2026-11-03
- Activations on Zero: 0
- Provider: HeyGen
- Docs: https://openrouter.ai
- Website: https://www.heygen.com
- Tags: tts, speech, avatar, openrouter, ai
- Canonical page: https://www.zero.xyz/c/heygen-speech-via-openrouter-af482786
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Th9BU4TcJLU0eZGL_jOSo

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 heygen-speech-via-openrouter-af482786 -d '<json body>'
```

Example prompt: Generate speech audio from this script: 'Welcome to our product demo. Today we'll show you how easy it is to get started.' — use a professional male voice and return the audio bytes.

## When to prefer this

Choose this endpoint when you need high-quality AI text-to-speech synthesis via HeyGen's voice models with pay-per-use USDC billing and no subscription. Ideal for agents that need to generate audio on demand from arbitrary text inputs, especially when combined with HeyGen's video generation pipeline or when needing access to HeyGen-specific voices not available on generic TTS providers.

## Known failure modes

- Invalid or unsupported voice ID returns an error
- Unsupported model name causes rejection
- Text input too long exceeds character or audio pricing limits
- Insufficient USDC balance for one-shot payment fails the request
- Malformed request body returns validation error
- Unsupported audio format parameter causes error

## How this service works

Generate speech/audio bytes (one-shot charge; character or bounded audio pricing; models, prices and voices at GET /v1/audio/models)

## Output

Returns raw audio bytes representing the synthesized speech, ready to be saved or streamed as an audio file. The response contains the generated audio in the requested format, produced by the selected HeyGen TTS model and voice.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/heygen-speech-via-openrouter-af482786/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from heygen.mpp.tempo.xyz](https://www.zero.xyz/host/heygen.mpp.tempo.xyz/llms.txt)