https://github.com/transformrs/trf
Multimodal AI command line interface (supports OpenAI, DeepInfra, Google, and others)
https://github.com/transformrs/trf
Last synced: about 1 year ago
JSON representation
Multimodal AI command line interface (supports OpenAI, DeepInfra, Google, and others)
- Host: GitHub
- URL: https://github.com/transformrs/trf
- Owner: transformrs
- Created: 2025-02-14T18:32:14.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-01T09:25:05.000Z (about 1 year ago)
- Last Synced: 2025-06-26T11:58:04.999Z (about 1 year ago)
- Language: Rust
- Homepage:
- Size: 28.3 KB
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
Awesome Lists containing this project
README
trf: Multimodal AI in the terminal
Supports OpenAI, DeepInfra, Google, Hyperbolic, and others
## Key Features
You can convert text to speech (tts) and, for example, play it from the command line:
```sh
$ export OPENAI_KEY="$(grep 'OPENAI_KEY' .env | cut -d= -f2)"
$ cat myfile.txt | trf tts | vlc - --intf dummy
```
Or generate an image from text:
```sh
$ export DEEPINFRA_KEY="$(grep 'DEEPINFRA_KEY' .env | cut -d= -f2)"
$ echo "A photo of a beach in Hawaii" | cargo run -- --verbose tti \
--model=black-forest-labs/FLUX-1-dev \
--output=myfile --width=1024 --height=1024 --steps=25
$ ls myfile*
myfile.png
```
You can also chat with an LLM:
```sh
$ export DEEPINFRA_KEY="$(grep 'DEEPINFRA_KEY' .env | cut -d= -f2)"
$ echo "This is a test. Respond with 'hello world'." | trf chat
hello world
```
## Installation
```sh
cargo install trf
```
or via [`cargo-binstall`](https://github.com/cargo-bins/cargo-binstall):
```sh
cargo binstall trf
```
For a list of supported providers, see the table in the [transformrs](https://github.com/rikhuijzer/transformrs) README.
## More Examples
### Text to Speech in Bash
We can read a file out loud from the command line.
For example, with the OpenAI API:
```sh
$ OPENAI_KEY="$(cat /path/to/key)"; cat myfile.txt | trf tts | vlc - --intf dummy
```
Here, we set the key, print the file `myfile.txt` to stdout, pipe it to `trf` to generate mp3 audio, and pipe that to `vlc` to play it.
The `--intf dummy` is optional; it just prevents `vlc` from opening a GUI.
One way to make this easier to use is to create a Bash script that sets the environment variable and runs the command.
For example, create a file called `spk.sh` (abbreviation for "speak") with the following content:
```bash
#!/usr/bin/env bash
# Exit on (pipe) errors.
set -euo pipefail
export OPENAI_KEY="$(cat /path/to/key)"
trf tts | vlc - --intf dummy
```
After adding `spk.sh` to your PATH, you can use it like this:
```sh
$ cat myfile.txt | spk
```
### Other Text to Speech Commands
```sh
$ DEEPINFRA_KEY="$(cat /path/to/key)"; cat myfile.txt | trf tts | vlc -
```
```sh
$ DEEPINFRA_KEY="$(cat /path/to/key)"; cat myfile.txt | trf tts --output myfile.mp3
```
### Chat in Bash
We can chat straight from the command line.
For example, via the DeepInfra API:
```sh
$ DEEPINFRA_KEY=""; echo "hi there" | trf chat
```
This defaults to the `meta-llama/Llama-3.3-70B-Instruct` model.
We can also create a Bash script to provide some default settings to the chat.
For example, create a file called `chat.sh` with the following content:
```bash
#!/usr/bin/env bash
export OPENAI_KEY="$(cat /path/to/key)"
trf chat --model="gpt-4o"
```
and add it to your PATH.
Now, we can use it like this:
```sh
$ echo "This is a test. Respond with 'hello'." | trf chat
hello
```
Or we can run a spellcheck on a file:
```sh
$ echo "Do you see spelling errors in the following text?"; cat myfile.txt | trf chat
```
Here is a more complex example.
For example, create a file called `writing-tips.sh` with the following content:
```bash
#!/usr/bin/env bash
set -euo pipefail
export DEEPINFRA_KEY="$(cat /path/to/key)"
PROMPT="
You are a helpful writing assistant.
Respond with a few suggestions for improving the text.
Use plain text only; no markdown.
Here is the text to check:
"
MODEL="deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
(echo "$PROMPT"; cat README.md) | trf chat --model="$MODEL"
```
## Philosophy
The philosophy of this project is mainly to not handle state.
Like curl or ffmpeg, this should make it easier to use in scripts and to share examples online.
Settings are done via command line arguments and environment variables.