Meet Fish Audio S1: The Expressive TTS Model to Clone Your Voice (Step-by-Step)

We have all heard how artificial intelligence (AI)-generated sound sounds like; it is robotic, flat, and lacking the feel of human emotions. Unfortunately, we have grown accustomed to the monotonous voice of GPS directions and the stilted narration of automated customer service lines. Have you ever wondered what if AI could sound more human with the warmth of a storyteller, the excitement of an announcer, or the empathy of a friend? There is a new text-to-speech (TTS) model called Fish Audio's S1 that might be able to do just that.

What is Fish Audio S1?

Fish Audio S1 is a next-generation text-to-speech model designed to produce incredibly natural and expressive audio. It's the culmination of extensive research and development, building upon the company's "Fish Speech" series to deliver a truly immersive listening experience. The company's goal is to rival the quality of professional voice actors, and with S1, they are closer than ever to achieving that.

Fish Audio allows you to generate expressive AI speech from text and allows you to control emotions. You can also clone your voice that sounds just like you, and even turn speech into text. The tool is great for video voiceovers, audiobook narration, character voices, and conversational chatbots, providing emotions and natural tone to characters, videos, and AI chatbots.

Here are some of the standout features of Fish Audio S1:

• Expressive TTS with emotion control: Generate speech that carries tone and rhythm (e.g., calm, curious, energetic) rather than flat reads, useful for narrative content and character work.
• Instant voice cloning: Create a custom voice with just 15 seconds of audio; suitable for brand voices, creator personas, and localized presenters.
• Cost-Effective Solution: Company claims S1 is ~6x cheaper than ElevenLabs, with 20K active developers and $5M in ARR, showing both price pressure and real usage at scale.

How to clone your voice using Fish Audio S1:

Using this AI tool is straightforward and easy.

Step 1: Visit the Fish Audio website, and you will instantly see the text-to-speech (TTS) option. Next to it will be the voice cloning feature, and finally, the Speech-to-Text (STT) option.

• Although you can test its features without signing up first, we recommend signing up to access all its features and capabilities.

Step 2: The voice generation and cloning features are under the products option. For this article, I will be cloning my own voice.

Step 3: To clone your voice:

• Go to the voice cloning option.
• Give your voice a name so you and or others can find it easily.
• Upload a recording of your voice or record it on the spot, then click Create.

Step 4: To test how Fish Audio has cloned your voice.

• Go to the text-to-speech option under products.
• Add the text you want your voice to say.
• Click Select Voice Model, and you will find your cloned voice instantly.
• Click generate and play.

In Conclusion:

You can do more than just clone your voice using Fish Audio; there are options that allow you to clone celebrities' voices. At the same time, there are already powerful AI voice generation tools in the market, like ElevenLabs, that have been the go-to tool for many users seeking an AI audio generator and voice cloning tool. However, if you want to try something different, you can give Fish Audio a try by cloning your own voice or checking out existing audio samples. If you like S1 over Elevenlabs, it can be an easy new addition to your stack.