Copies a speaker's voice
Add a reference audio clip and the speech takes on the voice characteristics of the speaker in it.
Clone a voice
Tada TTS 1B Text-to-Speech
A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. Lighter 1B variant
Made by Hume AI100 creditsper run Pro
Opens the audio studio with Tada TTS 1B Text-to-Speech ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Tada TTS 1B Text-to-Speech 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 TTS 1B Text-to-Speech
Tada TTS 1B Text-to-Speech, from Hume AI, does voice cloning. You give it a reference audio clip and some text. It speaks the text with the voice characteristics of the speaker in the clip. You get the speech back as an audio file.
You must provide two things: the audio clip, and the Prompt, which is the text to speak. Transcript is the words spoken in your clip. It is optional for English and required for any other language, because the built-in speech recognition understands English only. Language has ten code choices and starts on en. For non-English speech, pick the code that matches your clip.
Speed Up Factor runs from 0.5 to 2 and starts at 1. Values above 1 speed the speech up and values below 1 slow it down. Temperature must be above 0, goes up to 2 and starts at 0.6. Higher values give more varied output. Tada TTS 1B Text-to-Speech costs 100 credits.
Other models for this job
Same job: clone a voice. Compare before you choose.
Audio Pro Open
Tada Text-to-Speech 3BClone a voice
A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.
Open Source100 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
Transcript for non-English clips
Transcript is required when the reference audio is not in English.
How to use Tada TTS 1B Text-to-Speech
How It Works
How It Works
01
Add the reference audio
Add an audio clip of the speaker whose voice you want to copy.
02
Write the prompt
Type the text to speak in Prompt. For non-English audio, add its Transcript and pick the matching Language.
03
Generate
Run the model to get the speech back as an audio file.
Tip Speed Up Factor above 1 speeds the speech up and below 1 slows it down.
Good for
Narration in a chosen voice
Provide a clip of a speaker and have new text read in that voice.
Speech from a non-English clip
Add a reference clip in another language, fill in its Transcript and pick the matching Language.
Questions
Quick answers to help you get the most out of Tada TTS 1B Text-to-Speech in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. What does it cost?