---
title: "HeyGen Starfish Text-to-Speech API & Playground - Comfy"
description: "HeyGen Starfish Text-to-Speech: Synthesizes speech with a HeyGen voice that supports the Starfish engine. Run it in your browser or call it via API."
canonical: https://comfy.org/hub/models/heygen-starfish-text-to-speech/
lang: en
index: https://comfy.org/llms.txt
---

[Back to all models](https://comfy.org/hub/models/)

Heygen

[Audio](https://comfy.org/hub/models/?useCase=audio)

# HeyGen Starfish Text-to-Speech

Synthesizes speech with a HeyGen voice that supports the Starfish engine.

Cost depends on your settings.

- [audio](https://comfy.org/hub/models/?q=audio)
- [tts](https://comfy.org/hub/models/?q=tts)

[Read docs](https://docs.comfy.org/development/comfy-router/models#heygen)

Input

Speech text

Enter the words to speak, using SSML markup only when that format is selected.

Language

Choose a language, or leave unset to detect it from the speech text.

Locale

Choose a regional pronunciation, or leave unset to use the language. A selected locale overrides Language.

Advanced settings

Text format

Choose plain text or SSML markup for the speech input.

Speech speed

Output

Example

00:00

## Try an example

- This is the last song of the night on Harbour Radio, and the fog is coming in low over the water. If you're driving, slow down on the coast road; the lights past the bridge are out again. Leave the window open a crack, let the foghorn keep time, and we'll be back at six with the tide tables and whatever the gulls have to say. Sleep well, Harbourside.

## More models

[Browse all Browse all models](https://comfy.org/hub/models/)

- [ElevenLabs

  ### ElevenLabs Text-to-Dialogue

  Text to Audio

  elevenlabs audio tts dialogue multi-speaker](https://comfy.org/hub/models/elevenlabs-text-to-dialogue/)
- [ByteDance

  ### Seed Audio 1.0 Text-to-Speech

  Text to Audio

  byteplus seed-audio audio tts](https://comfy.org/hub/models/seed-audio-1-0-text-to-speech/)
- [ByteDance

  ### Seed Audio 1.0 Multilingual Text-to-Speech

  Text to Audio

  byteplus seed-audio multilingual audio tts recommended](https://comfy.org/hub/models/seed-audio-1-0-multilingual-text-to-speech/)
- [Black Forest Labs

  ### FLUX 3 Video

  Text to Video

  bfl flux-3 video text-to-video audio](https://comfy.org/hub/models/flux-3-video-text-to-video/)