# Chatterbox Turbo
**URL:**
**Author:**  [@taniaM10](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FtaniaM10)%5C
**Post date:** [December 19, 2025, 6:37pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F1 "2025-12-19T18:37:52Z")
Hello everyone. When installing Chatterbox Turbo locally, I encountered this error. Please help me fix it. New tokens were created, but the problem persists.
”huggingface\_hub.errors.LocalTokenNotFoundError: Token is required (`token=True`), but no token found. You need to provide a token or be logged in to Hugging Face with `hf auth login` or `huggingface_hub.login`. See [Hugging Face – The AI community building the future.](https://huggingface.co/settings/tokens) .
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [December 19, 2025, 6:37pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F2 "2025-12-19T18:37:53Z")
Unlisted on December 19, 2025, 6:37pm UTC
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [December 20, 2025, 3:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F3 "2025-12-20T03:18:01Z")
Listed on December 20, 2025, 3:18am UTC
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 20, 2025, 6:27am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F4 "2025-12-20T06:27:38Z")
The method for setting environment variables varies depending on your OS, but I think setting the `HF_TOKEN` environment variable is the simplest approach. For greater reliability, use `hf auth login`.
* * *
This error means one specific thing: **some code called Hugging Face Hub with `token=True`, and your runtime could not find a locally stored Hugging Face token.** Creating new tokens on the Hugging Face website does not fix anything unless the token is actually available inside the environment that runs Chatterbox Turbo.
* * *
## What the error means (background)
Hugging Face Hub download functions accept a `token` argument with these semantics:
- `token=True` means “read the token from the Hugging Face config folder.”
- `token=False` or `None` means “do not use a token.”
- `token="hf_..."` means “use this token string explicitly.” ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/file_download "Downloading files"))
Your traceback says: `Token is required (token=True), but no token found.`
So the code path is explicitly requesting `token=True`, and the library is failing because it cannot find a cached login token.
* * *
## Why this happens specifically with Chatterbox Turbo
In the official Hugging Face Space code for Chatterbox Turbo, `from_pretrained()` downloads weights via `snapshot_download()` like this:
- `token=os.getenv("HF_TOKEN") or True` ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
That line causes your exact failure mode:
- If `HF_TOKEN` environment variable is set, it uses it.
- If `HF_TOKEN` is not set (or is empty), it falls back to `True`.
- `True` triggers “must read cached token from disk,” and if none is found, you get `LocalTokenNotFoundError`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/file_download "Downloading files"))
So you can see this error even when downloading a public model repo, because the code forces auth unless `HF_TOKEN` exists.
* * *
## Root causes in real local installs (most common)
### Cause 1: You created tokens online, but did not log in locally
Creating a token at `huggingface.co/settings/tokens` only creates credentials.
Your machine still has no saved token unless you do **one** of these:
- Set `HF_TOKEN` in the environment.
- Run `hf auth login` to save the token locally. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
### Cause 2: You logged in, but you are running under a different user or “different home”
This is extremely common with:
- `sudo python ...`
- Docker containers
- systemd services
- remote processes
- IDE run configs that do not inherit your shell env
Hugging Face stores the token under `HF_HOME` (default `~/.cache/huggingface`) and by default the token file is at `~/.cache/huggingface/token`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
If your process runs with a different home directory, it will not see the saved token.
### Cause 3: You set the wrong environment variable
`huggingface_hub` standardizes on:
- `HF_TOKEN`
- `HF_HOME`
- `HF_TOKEN_PATH` ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
If you set something else, Chatterbox Turbo still sees `HF_TOKEN` as missing and falls back to `True`. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
* * *
## Fixes that work reliably
### Fix A (most reliable): Set `HF_TOKEN` where you run Chatterbox Turbo
This avoids all “where is the token file” issues.
**Linux/macOS (bash/zsh):**
```bash
export HF_TOKEN="hf_your_token_here"
python -c "import os; print(bool(os.getenv('HF_TOKEN')))"
```
**Windows PowerShell:**
```powershell
$env:HF_TOKEN="hf_your_token_here"
python -c "import os; print(bool(os.getenv('HF_TOKEN')))"
```
Why this fixes it: Chatterbox Turbo checks `HF_TOKEN` first, and only falls back to `token=True` if it is missing. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
Also, `HF_TOKEN` overrides any token stored on disk. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
### Fix B: Log in locally with the Hugging Face CLI
Run:
```bash
hf auth login
hf auth whoami
```
The docs state `hf auth login` validates and saves the token to `HF_HOME` (default `~/.cache/huggingface/token`), and other libraries reuse it automatically. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
If `hf auth whoami` works but your app still fails, you are almost certainly hitting the “different user / different `HF_HOME`” pitfall.
### Fix C (Jupyter/Notebook): Login programmatically
If you run in a notebook kernel that does not inherit your shell login, use the Python authentication API. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/authentication "Authentication"))
Example (do not paste tokens into shared notebooks):
```python
from huggingface_hub import login
login("hf_your_token_here")
```
* * *
## Quick verification checklist (pinpoint the exact mismatch)
Run these **in the same terminal/session** that launches Chatterbox Turbo:
1. Confirm the environment variable path:
```bash
python -c "import os; print('HF_TOKEN set:', bool(os.getenv('HF_TOKEN')))"
```
1. Check where Hugging Face is looking for the token:
```bash
python -c "import os; print('HF_HOME=', os.getenv('HF_HOME')); print('HF_TOKEN_PATH=', os.getenv('HF_TOKEN_PATH'))"
```
What matters:
- If `HF_TOKEN` is falsey, Chatterbox Turbo will force `token=True` and require a cached token. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
- If `HF_HOME` is set to something unexpected, your login token may be saved somewhere else. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
1. Confirm CLI login state:
```bash
hf auth whoami
```
If this fails, you are not logged in for that user environment. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
* * *
## Workarounds if you want “no token required”
### Workaround 1: Patch the token forcing line
In `chatterbox/tts_turbo.py`, the forcing behavior is:
- `token=os.getenv("HF_TOKEN") or True` ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
If you change it to:
- `token=os.getenv("HF_TOKEN")`
then public downloads typically work without login, because `token` becomes `None` when unset, and “no token is provided.” ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/file_download "Downloading files"))
This is a local patch. Upstream updates can overwrite it.
### Workaround 2: Download once, then load from local directory
That same file includes a `from_local()` loader that takes a local checkpoint directory and loads weights from there. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
So you can:
1. download model files by any method you control (or on another machine),
2. copy them into a directory,
3. call `from_local(path, device)` instead of `from_pretrained(device)`.
This is also the path you use on offline machines.
* * *
## Extra context: token storage and common “it still doesn’t work” pitfalls
### Token storage locations
- `HF_HOME` defaults to `~/.cache/huggingface`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
- Token path defaults to `"$HF_HOME/token"` (so typically `~/.cache/huggingface/token`). ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
- Setting `HF_TOKEN` overrides the stored token. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
### Pitfall: `sudo` breaks it
If you ran `hf auth login` as your normal user but run the app with `sudo`, root has a different `~` and a different `HF_HOME`. Result: no token found.
### Pitfall: Docker breaks it unless you pass env or mount cache
Inside Docker, you usually need either:
- `-e HF_TOKEN=...`
- or mount the Hugging Face cache directory into the container
### Pitfall: “token created” but wrong scope
For reading/downloading, a read token is typically sufficient. Hugging Face describes tokens and scopes in their security tokens docs. ([Hugging Face](https://huggingface.co/docs/hub/en/security-tokens "User access tokens"))
* * *
## References (URLs)
```plaintext
https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py
https://huggingface.co/docs/huggingface_hub/en/package_reference/file_download
https://huggingface.co/docs/huggingface_hub/en/quick-start
https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables
https://huggingface.co/docs/huggingface_hub/en/guides/cli
https://huggingface.co/docs/huggingface_hub/en/package_reference/authentication
```
* * *
## Summary
- Your error persists because Chatterbox Turbo’s `from_pretrained()` forces `token=True` when `HF_TOKEN` is missing. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
- Creating tokens online is not enough. You must either set `HF_TOKEN` or run `hf auth login` in the same runtime environment. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
- If it still fails after login, the cause is almost always “different user / different `HF_HOME`.” ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
- Fastest reliable fix: set `HF_TOKEN` in the exact shell/container that runs Chatterbox Turbo. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
---
**Author:**  [@taniaM10](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FtaniaM10)%5C
**Post date:** [December 22, 2025, 6:47pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F5 "2025-12-22T18:47:38Z")
I’m sorry, I’m just learning. As far as I understand, I don’t have an “hf\_token” environment. I don’t know which specific commands to use or how to set up the environment.
(venv) C:\Chatterbox Turbo\chatterbox-turbo-demo\>python -c “import os; print(‘HF\_TOKEN set:’, bool(os.getenv(‘HF\_TOKEN’)))”
HF\_TOKEN set: False
(venv) C:\Chatterbox Turbo\chatterbox-turbo-demo\>python -c “import os; print(‘HF\_HOME=’, os.getenv(‘HF\_HOME’)); print(‘HF\_TOKEN\_PATH=’, os.getenv(‘HF\_TOKEN\_PATH’))”
HF\_HOME= None
HF\_TOKEN\_PATH= None
(venv) C:\Chatterbox Turbo\chatterbox-turbo-demo\>hf auth whoami
Not logged in
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 22, 2025, 10:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F7 "2025-12-22T22:58:54Z")
I assume you are using Windows…
* * *
You are in the “expected broken” state for this project on Windows:
- `HF_TOKEN` env var is not set.
- `hf auth whoami` says “Not logged in”.
Chatterbox Turbo’s code does this when it downloads the model:
- `token = os.getenv("HF_TOKEN") or True` ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
So if `HF_TOKEN` is missing, it passes `True`. In `huggingface_hub`, `token=True` means “I must find a locally saved token.” If you are not logged in, there is no saved token, so you get `LocalTokenNotFoundError`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))
You fix it by giving Hugging Face a token in one of two beginner-friendly ways.
* * *
## Background: what an “environment variable” is (Windows-friendly)
An environment variable is just a named setting that programs can read. On Windows, you can set it:
- Temporarily, only for the current terminal window.
- Permanently, via Windows GUI (recommended for beginners), so every new terminal can see it.
`HF_TOKEN` is the standard environment variable name that Hugging Face uses for authentication, and it **overrides** any token saved on disk. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
Your venv is unrelated. A Python venv manages Python packages. It does not automatically create `HF_TOKEN`.
* * *
## Choose one: easiest two solutions
### Solution A (recommended): log in once with `hf auth login`
This stores the token so `token=True` can find it.
1. Make sure you have a token on the website (you already do). Prefer a **read** token for downloading models. Hugging Face recommends least privilege and separate tokens per machine. ([Hugging Face](https://huggingface.co/docs/hub/en/security-tokens "User access tokens"))
Tokens page: [https://huggingface.co/settings/tokens](https://huggingface.co/settings/tokens)
2. In the same terminal where you run Chatterbox Turbo (your `(venv) C:\Chatterbox Turbo\...>` prompt), run:
```bat
hf auth login
```
1. It will prompt for the token. Paste the token (starts with `hf_`). Do not add quotes.
2. Verify:
```bat
hf auth whoami
```
You should see your Hugging Face username. The CLI guide shows that login saves the token locally and then `whoami` works. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))
1. Run Chatterbox Turbo again.
Why this works: now when Chatterbox Turbo passes `token=True` (because `HF_TOKEN` is unset), Hugging Face Hub can find the saved token. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
* * *
### Solution B (Windows GUI): set `HF_TOKEN` permanently
This is often the most beginner-proof method because it avoids “where is my token saved” questions.
#### Step-by-step via Windows GUI
1. Open the environment variable editor:
- Press the Windows key and type **environment variables**
- Click either:
1. In the **User variables** section (top box), click **New…**
2. Enter:
- Variable name: `HF_TOKEN`
- Variable value: your token (starts with `hf_...`)
1. Click **OK** on all dialogs to save.
2. Important: close your terminal and open a **new** terminal. Many environment changes only appear in new processes.
3. Activate your venv again, then verify:
```bat
python -c "import os; print('HF_TOKEN set:', bool(os.getenv('HF_TOKEN')))"
```
You want `HF_TOKEN set: True`.
1. Run Chatterbox Turbo again.
Why this works: Chatterbox Turbo checks `os.getenv("HF_TOKEN")` first. If it exists, it uses that token and does not fall back to `True`. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
#### Security note (worth reading once)
Do not paste your token into code and commit it. Hugging Face explicitly warns against hardcoding tokens and recommends safer storage like environment variables. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
* * *
## Optional: set `HF_TOKEN` from the command line (if you prefer)
You asked for GUI, but these are handy.
### Temporary (current CMD window only)
```bat
set HF_TOKEN=hf_your_token_here
```
### Permanent (future terminals)
```bat
setx HF_TOKEN "hf_your_token_here"
```
`setx` writes to the registry and is available in **future** command windows, not the current one. ([Microsoft Learn](https://learn.microsoft.com/en-us/windows-server/administration/windows-commands/setx "setx"))
* * *
## If it still fails after login or setting `HF_TOKEN`
These are the usual Windows gotchas:
1. **You set `HF_TOKEN`, but you did not open a new terminal**
Open a new CMD/PowerShell window and re-check `HF_TOKEN set: True`. `setx` in particular requires a new window. ([Microsoft Learn](https://learn.microsoft.com/en-us/windows-server/administration/windows-commands/setx "setx"))
2. **You are launching from an IDE that does not inherit your environment**
If you run from VS Code / PyCharm, set `HF_TOKEN` in that run configuration or use the CLI login method.
3. **Token pasted with extra characters**
Paste only the token string (starts `hf_`). No quotes, no spaces.
4. **You used the old command name**
Current docs use `hf auth login` and `hf auth whoami`. The HF blog shows the migration from `huggingface-cli login` to `hf auth login`. ([Hugging Face](https://huggingface.co/blog/hf-cli "Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨"))
* * *
## Links
- Hugging Face Hub Quickstart (HF\_TOKEN and warnings about hardcoding): [https://huggingface.co/docs/huggingface\_hub/en/quick-start](https://huggingface.co/docs/huggingface_hub/en/quick-start) ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
- Hugging Face Hub env vars (HF\_TOKEN, HF\_HOME, HF\_TOKEN\_PATH): [https://huggingface.co/docs/huggingface\_hub/en/package\_reference/environment\_variables](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables) ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
- Hugging Face CLI guide (auth login, whoami, saved token): [https://huggingface.co/docs/huggingface\_hub/en/guides/cli](https://huggingface.co/docs/huggingface_hub/en/guides/cli) ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))
- Chatterbox Turbo demo code showing `HF_TOKEN` fallback: [https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts\_turbo.py](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py) ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/chatterbox/tts_turbo.py "chatterbox/tts\_turbo.py · ResembleAI/chatterbox-turbo-demo at main"))
* * *
## Summary
- Your machine has no Hugging Face auth set up. That is why `token=True` fails. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))
- Fix option A: `hf auth login` then `hf auth whoami`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/guides/cli "Command Line Interface (CLI)"))
- Fix option B: set `HF_TOKEN` via Windows GUI User variables, reopen terminal, verify `HF_TOKEN set: True`. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/package_reference/environment_variables "Environment variables"))
- Do not hardcode tokens. Use env vars. ([Hugging Face](https://huggingface.co/docs/huggingface_hub/en/quick-start "Quickstart"))
---
**Author:**  [@taniaM10](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FtaniaM10)%5C
**Post date:** [December 23, 2025, 7:44pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F8 "2025-12-23T19:44:29Z")
Thank you! It helped me install it using the command line. The installation was successful up to this point:
Traceback (most recent call last):
File “C:\Chatterbox Turbo\chatterbox-turbo-demo\app.py”, line 164, in
demo.queue().launch(
TypeError: Blocks.launch() got an unexpected keyword argument ‘css’ 😑
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 23, 2025, 8:58pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F9 "2025-12-23T20:58:40Z")
Gradio has poor compatibility when versions change, so either lock the version or use the version recommended by the software…
* * *
That traceback is a Gradio version mismatch.
Your `app.py` calls:
```py
demo.queue().launch(mcp_server=True, css=CUSTOM_CSS, ssr_mode=False)
```
You can see `css=` is passed into `launch()` in the upstream demo code. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/app.py "app.py · ResembleAI/chatterbox-turbo-demo at main"))
But the Gradio version you have installed does not support `css` as a `launch()` keyword, so Python raises:
> `TypeError: Blocks.launch() got an unexpected keyword argument 'css'`
This is exactly what happens when code written for one Gradio API is run on a different Gradio major version.
* * *
## Background: why this happens (Gradio 5 vs Gradio 6)
Gradio made a breaking change around v6:
- In **Gradio 5.x** , app-level settings like `css`, `theme`, `js`, `head` lived on the **`gr.Blocks(...)` constructor**.
- In **Gradio 6.x** , those app-level settings were **moved to `Blocks.launch(...)`**. ([Gradio](https://www.gradio.app/main/guides/gradio-6-migration-guide "Gradio 6 Migration Guide"))
So:
- If your code does `demo.launch(css="...")`, it expects **Gradio 6.x** behavior. ([Gradio](https://www.gradio.app/main/guides/gradio-6-migration-guide "Gradio 6 Migration Guide"))
- If you are on **Gradio 5.x** , `launch()` won’t accept `css=` and you get your exact error.
There is also a clue in the demo repo itself:
- `requirements.txt` pins **`gradio==5.44.1`**. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/requirements.txt "requirements.txt · ResembleAI/chatterbox-turbo-demo at main"))
- The Space metadata (README frontmatter) says **`sdk_version: 6.0.2`**. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/resolve/main/README.md?download=true "293 Bytes"))
So the upstream demo currently mixes signals: code looks like Gradio 6-style (`css` in `launch`), while `requirements.txt` pins Gradio 5. That is why local installs often trip here.
* * *
## Step 1: Confirm your installed Gradio version (Windows CMD)
In your venv:
```bat
python -c "import gradio as gr; print(gr. __version__ )"
pip show gradio
```
If you see `5.x` (very likely), that explains the error.
* * *
# Fix path A (recommended): Upgrade Gradio to match the code (Gradio 6)
This is usually the cleanest because your `app.py` is already written in the “css in launch” style used in Gradio 6. ([Gradio](https://www.gradio.app/main/guides/gradio-6-migration-guide "Gradio 6 Migration Guide"))
### A1) Upgrade Gradio inside your venv
Pick one of these:
**Match the Space config exactly (likely safest):**
```bat
pip install --upgrade "gradio==6.0.2"
```
**If you want MCP support (because your code uses `mcp_server=True`):**
Gradio’s MCP guide says to install the MCP extra: `pip install "gradio[mcp]"`. ([Gradio](https://www.gradio.app/guides/building-mcp-server-with-gradio "Building Mcp Server With Gradio"))
So you can do:
```bat
pip install --upgrade "gradio[mcp]==6.0.2"
```
### A2) Re-check version
```bat
python -c "import gradio as gr; print(gr. __version__ )"
```
### A3) Run again
```bat
python app.py
```
### A4) Prevent a downgrade later
If you re-run `pip install -r requirements.txt` and that file still pins `gradio==5.44.1`, it can downgrade you again. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/requirements.txt "requirements.txt · ResembleAI/chatterbox-turbo-demo at main"))
So either:
- edit `requirements.txt` to `gradio==6.0.2`, or
- remove the `gradio==...` line entirely and install Gradio separately.
* * *
# Fix path B: Keep Gradio 5 and change `app.py` to the Gradio 5 style
If you prefer not to upgrade, you can “move css back” into the `Blocks()` constructor, which is how Gradio 5 expects it. (This is the inverse of the Gradio 6 migration note.) ([Gradio](https://www.gradio.app/main/guides/gradio-6-migration-guide "Gradio 6 Migration Guide"))
### B1) Change the `Blocks` line
Find:
```py
with gr.Blocks(title="Chatterbox Turbo") as demo:
```
Change to:
```py
with gr.Blocks(title="Chatterbox Turbo", css=CUSTOM_CSS) as demo:
```
### B2) Remove `css=` from `launch()`
Change:
```py
demo.queue().launch(
mcp_server=True,
css=CUSTOM_CSS,
ssr_mode=False
)
```
To:
```py
demo.queue().launch(
mcp_server=True,
ssr_mode=False
)
```
If you hit another “unexpected keyword argument” after that, do the most minimal launch first:
```py
demo.queue().launch()
```
Then add options back one at a time.
* * *
## Which fix should you choose?
- Choose **Fix A (upgrade to Gradio 6)** if you want the code to match what the Space is configured to use (`sdk_version: 6.0.2`). ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/resolve/main/README.md?download=true "293 Bytes"))
- Choose **Fix B (edit code)** if you want to keep your current Gradio 5 install and avoid more Gradio 6 breaking changes.
In practice, for this repo, upgrading is usually simplest because the current `app.py` already uses Gradio 6-style `launch(css=...)`. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/app.py "app.py · ResembleAI/chatterbox-turbo-demo at main"))
* * *
## Summary
- The error means “your Gradio version’s `launch()` does not support `css=`.”
- Your `app.py` passes `css=` into `launch()`, which matches Gradio 6 behavior. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/blob/main/app.py "app.py · ResembleAI/chatterbox-turbo-demo at main"))
- Fix it either by upgrading to Gradio 6.0.2 (recommended) or moving `css` into `gr.Blocks(..., css=...)` for Gradio 5. ([Hugging Face](https://huggingface.co/spaces/ResembleAI/chatterbox-turbo-demo/resolve/main/README.md?download=true "293 Bytes"))
---
**Author:**  [@taniaM10](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FtaniaM10)%5C
**Post date:** [December 25, 2025, 8:22pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchatterbox-turbo%2F171768%2F10 "2025-12-25T20:22:10Z")
Thank you, it gave me a link. But unfortunately, it doesn’t generate anything. I enter a single word, but it generates forever. The window still displays “Text to synthesize (max chars 300)”.
the code is like this:
(venv) C:\Chatterbox Turbo\chatterbox-turbo-demo\>python app.py
Fetching 10 files: 100%|███████████████████████████████████████████████████████████████████████| 10/10 [00:00\