# AI use cases for Chatterbox (resemble-ai/chatterbox) Repo: [resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox) | Use cases: 3 | Page: https://dedupedai.com/use-cases/resemble-ai-chatterbox/ Chatterbox is Resemble AI's family of open-source text-to-speech models. Chatterbox-Turbo (350M) targets low-latency English voice agents with native paralinguistic tags like [laugh] and [chuckle], Chatterbox-Nano (110M) runs on CPU, and Chatterbox Multilingual V3 (500M) covers 23+ languages with zero-shot voice cloning from a short reference clip. Every output carries Resemble's Perth watermark. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Generate speech in a cloned voice with laughs and pauses: https://dedupedai.com/use-cases/resemble-ai-chatterbox/clone-a-voice-with-chatterbox-turbo/ - Narrate the same text in many languages: https://dedupedai.com/use-cases/resemble-ai-chatterbox/narrate-in-23-languages-with-chatterbox-multilingual/ - Run on-device speech on a CPU with Chatterbox-Nano: https://dedupedai.com/use-cases/resemble-ai-chatterbox/run-tts-on-cpu-with-chatterbox-nano/ ## How to generate speech in a cloned voice with laughs and pauses with Chatterbox Repo: [resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use Chatterbox-Turbo with a 10 second reference clip and paralinguistic tags for natural sounding lines. **Who it is for:** A developer prototyping a phone or support voice agent. **The problem:** Flat TTS voices sound robotic in conversation. **The outcome:** A WAV file in the reference voice with tags like [chuckle] rendered. ### Steps 1. Install with `pip install chatterbox-tts` 2. Load ChatterboxTurboTTS.from_pretrained with device set to cuda 3. Call model.generate with your text and audio_prompt_path pointing to your reference clip 4. Save the result with torchaudio as in the README ### Prompt to paste into your agent ```text Using resemble-ai/chatterbox, install `pip install chatterbox-tts`, write a script with ChatterboxTurboTTS that reads in the voice from , adding [chuckle] where it fits, and saves one WAV per line. ``` ### Caveat This card is written from the resemble-ai/chatterbox README, not from a test run by Deduped. Before you start, make sure you have Python 3.11. Check the repo for newer instructions before you rely on these steps. Risk, data: Only clone voices you have permission to use; outputs carry the Perth watermark. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/resemble-ai-chatterbox/clone-a-voice-with-chatterbox-turbo/ ## How to narrate the same text in many languages with Chatterbox Repo: [resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Use Chatterbox Multilingual V3 to generate French, Chinese and 20+ other languages from one model. **Who it is for:** A creator localizing videos or courses. **The problem:** Separate TTS vendors per language get expensive and inconsistent. **The outcome:** WAV files in each target language, optionally in one consistent voice. ### Steps 1. Install with `pip install chatterbox-tts` 2. Load ChatterboxMultilingualTTS.from_pretrained with t3_model set to v3 3. Call generate with your text and language_id such as fr or zh 4. Make sure any reference clip matches the language tag to avoid accent transfer ### Prompt to paste into your agent ```text With resemble-ai/chatterbox, load ChatterboxMultilingualTTS with t3_model="v3" and generate in French, Spanish and Hindi using language_id, saving each as a WAV. ``` ### Caveat The Single Language Pack has dedicated finetunes for some languages if you need tighter quality. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/resemble-ai-chatterbox/narrate-in-23-languages-with-chatterbox-multilingual/ ## How to run on-device speech on a CPU with Chatterbox-Nano with Chatterbox Repo: [resemble-ai/chatterbox](https://github.com/resemble-ai/chatterbox) | Difficulty: Beginner | Time: 20 minutes | Basis: From the README Load the 110M Nano model through the Turbo class to generate speech without a GPU. **Who it is for:** A developer targeting laptops, edge boxes or cheap servers. **The problem:** Most good TTS models need a GPU. **The outcome:** Speech generated on CPU with the same tag support as Turbo. ### Steps 1. Install with `pip install chatterbox-tts` 2. Load ChatterboxTurboTTS.from_pretrained with nano=True and device set to cpu 3. Call model.generate with your text and a reference clip 4. Save the WAV and compare speed with Turbo ### Prompt to paste into your agent ```text Using resemble-ai/chatterbox, write a CPU-only script that loads ChatterboxTurboTTS with nano=True and device cpu, generates , and times the run. ``` ### Caveat This card is written from the resemble-ai/chatterbox README, not from a test run by Deduped. Before you start, make sure you have Python 3.11. Check the repo for newer instructions before you rely on these steps. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/resemble-ai-chatterbox/run-tts-on-cpu-with-chatterbox-nano/