Starfish

Generate speech from your text using HeyGen’s TTS in-house model

1. Auth

Step	What to do
Get key	HeyGen → Settings → API token
Send it	Header: `X-API-KEY: <your_token>` on every request

2. List compatible voices

Get public and custom voices that work with Starfish TTS. Use a voice_id from this response when calling Text-to-Speech.

Item	Value
Endpoint	`GET https://api.heygen.com/v1/audio/voices`
Docs	List Compatible Voices

curl -X GET "https://api.heygen.com/v1/audio/voices" \
  -H "X-API-KEY: $HEYGEN_API_KEY"

3. Generate speech (Text-to-Speech — Starfish)

Item	Value
Endpoint	`POST https://api.heygen.com/v1/audio/text_to_speech`
Docs	Text-to-Speech — Starfish

Body (JSON): include at least text and voice_id. Example:

{
  "text": "Your script or message to speak.",
  "voice_id": "<voice_id from GET /v1/audio/voices>"
}

curl -X POST "https://api.heygen.com/v1/audio/text_to_speech" \
  -H "X-API-KEY: $HEYGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello from HeyGen Starfish.", "voice_id": "YOUR_VOICE_ID"}'

The response contains the generated audio (e.g. URL or base64). Use it in video generation or for playback.

Summary

Step	Endpoint	Purpose
1	`GET /v1/audio/voices`	List voices → get `voice_id`
2	`POST /v1/audio/text_to_speech`	Send `text` + `voice_id` → get audio

Next

API Reference – Text-to-Speech
API Reference – List Compatible Voices
HeyGen Quick Start – auth and other API paths

Updated 1 day ago