Skip to content

Clone a voice

Tada Text-to-Speech 3B

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.

Made by Open Source100 creditsper run Pro
What it needs

Opens the audio studio with Tada Text-to-Speech 3B ready to use. You can look around as a guest. Running it takes the Pro plan or higher.

Sample output

What Tada Text-to-Speech 3B makes, what it needs and what you get

What it makes

Clone a voice

Learns a voice from a short sample so you can reuse it.

What you need

  • A short sample of the voice
  • What the voice should say

What you get

A reusable voice that sounds like the sample

  • WAV and MP3 files

About Tada Text-to-Speech 3B

Tada Text-to-Speech 3B clones a voice. You give it an audio clip of a speaker and some text, and it speaks that text in the speaker's voice. You get back an audio clip of the result.

You need to provide one audio clip and the Prompt, which is the text to speak. Transcript is a written version of the clip. It is optional for English clips. It is required when the clip is not in English, because the built-in speech recognition handles English only. Language has ten choices, and English is the starting one. Set it to match your text when the text is not English.

Speed Up Factor runs from 0.5 to 2. Above 1 it speeds the speech up and below 1 it slows it down. Temperature gives more varied output when raised. Tada Text-to-Speech 3B costs 100 credits, as does F5 TTS. Index TTS 2.0 costs 100 credits for 5s.

Other models for this job

Same job: clone a voice. Compare before you choose.

See all models for this job
Audio Pro Open
Tada TTS 1B Text-to-SpeechClone a voice

A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. Lighter 1B variant

Hume AI100 creditsper run
Audio Pro Open
Zonos-Audio-CloneClone a voice

Clone voice of any person and speak anything in their voice using zonos' voice cloning.

Zyphra100 creditsper run
Audio Pro Open
F5 TTSClone a voice

F5 TTS

Open Source20 creditsper run
Audio Pro Open
Zonos2Clone a voice

Zonos2 is a text-to-speech model that clones a voice from a short sample and speaks naturally across many languages.

Zyphra8 creditsper 5 s

What it does well

Speaks in a reference voice

It replicates the voice of the speaker in the audio clip you give it.

Ten Language choices

English is the starting choice. Set Language to match your Prompt when the text is not in English.

Faster or slower speech

Speed Up Factor runs from 0.5 to 2. Values above 1 speed the speech up and values below 1 slow it down.

How to use Tada Text-to-Speech 3B

How It Works
01

Add a voice clip

Add one audio clip of the speaker whose voice you want to copy.

02

Write the text

Enter the words to speak in the Prompt. If your clip is not in English, add its Transcript. If your Prompt text is not in English, set Language to match.

03

Generate and listen

Generate, then play the new speech in the reference voice.

Tip Speed Up Factor starts at 1. Raise it to speed the speech up or lower it to slow the speech down.

Good for

Narration in your own voice

Add a clip of yourself, then have new text spoken in your voice.

One narrator for many scripts

Reuse the same reference clip so different texts are read in the same voice.

Questions

Quick answers to help you get the most out of Tada Text-to-Speech 3B in FunAI Studio.

1. What do I need to provide?
2. When do I need a Transcript?
3. How much does Tada Text-to-Speech 3B cost?