---
title: "Seed Audio 1 AI Voice Generator"
canonical: https://withicarus.com/models/seed-audio-1
site: Icarus
description: "Use Seed Audio 1, the audio model by ByteDance, on Icarus. Speech shaped by a written scene."
---

# Seed Audio 1 AI Voice Generator

Use Seed Audio 1, the audio model by ByteDance, on Icarus. Speech shaped by a written scene.

Audio model by ByteDance. Speech shaped by a written scene.

Try it: https://withicarus.com/dashboard/audio?tab=speech

## What it does

- Job: Text to Speech
- Voices: 21
- Longest script: 2,048 characters
- Your own voices: Yes
- Gives back: A sound file

## Price

- A second: $0.004

Every price: https://withicarus.com/pricing#audio-costs-heading

## Questions

### What is Seed Audio 1?

Seed Audio 1 is an audio model made by ByteDance. Speech shaped by a written scene. You can use it on Icarus.

### How many voices and languages does Seed Audio 1 have?

21 voices.

### What does Seed Audio 1 cost on Icarus?

$0.004 for a second. You see the price before you press Generate.

### Can I use Seed Audio 1 from Claude or ChatGPT?

Yes. Connect Icarus to Claude or ChatGPT once, then ask for Seed Audio 1 by name in plain words. The file comes back in the chat.

## More audio models

- [Gemini 3.8 Flash Speech](https://withicarus.com/models/gemini-3.8-flash-tts): Audio model by Google. Two-voice conversations, steered by a written note.
- [Eleven v4](https://withicarus.com/models/eleven-v4): Audio model by ElevenLabs. Natural, expressive reads you steer with tags like [whispers].
- [Eleven v4 Turbo](https://withicarus.com/models/eleven-v4-turbo): Audio model by ElevenLabs. The same natural reads, back sooner and at half the price.
- [Eleven v3](https://withicarus.com/models/eleven-v3): Audio model by ElevenLabs. Conversations between up to 10 voices, with tags like [laughs].
- [MiniMax Speech 2.8 HD](https://withicarus.com/models/minimax-speech-2.8-hd): Audio model by MiniMax. Long scripts, with the mood and tone set by you.
- [MiniMax Speech 2.8 Turbo](https://withicarus.com/models/minimax-speech-2.8-turbo): Audio model by MiniMax. The same voices and controls, back sooner.
- [Qwen Audio 3](https://withicarus.com/models/qwen-audio-3): Audio model by Qwen. Short, bright lines in 10 languages.
- [Seed Speech 2](https://withicarus.com/models/seed-speech-2): Audio model by ByteDance. The lowest price, steered by a written note.
- [Eleven Voice Changer](https://withicarus.com/models/eleven-voice-changer): Audio model by ElevenLabs. A new voice on your recording, same timing.
- [HeyGen Translate](https://withicarus.com/models/heygen-translate): Audio model by HeyGen. Your video in another language, lips in sync.
- [HeyGen Translate Fast](https://withicarus.com/models/heygen-translate-fast): Audio model by HeyGen. The same, back sooner for half the price.
- [Eleven Dubbing](https://withicarus.com/models/eleven-dubbing): Audio model by ElevenLabs. Another language in the same voice, for sound or video.


---

Site: Icarus (https://withicarus.com)
Canonical: https://withicarus.com/models/seed-audio-1
Contact: tanmay@hooked.design