Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
92 changes: 77 additions & 15 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -29,11 +29,15 @@ Homebrew pulls in `ffmpeg` and `portaudio`, so `transcribe`, `stream`, and `agen

### pipx / uv

With pipx:

```sh
# pipx
pipx install "git+https://github.com/AssemblyAI/cli.git"
```

# uv
Or with uv:

```sh
uv tool install "git+https://github.com/AssemblyAI/cli.git"
```

Expand Down Expand Up @@ -72,43 +76,89 @@ Checked before the keyring, so nothing is written to disk — ideal for CI (set

### Basic usage

Guided setup: sign in, first transcription, start building:

```sh
# Guided setup: sign in, first transcription, start building
assembly onboard
```

Transcribe the hosted sample:

# Transcribe the hosted sample, then your own audio
```sh
assembly transcribe --sample
```

Then your own audio:

```sh
assembly transcribe call.mp3
```

Stream the microphone live (Ctrl-C to stop):

# Stream the microphone live (Ctrl-C to stop)
```sh
assembly stream
```

# Talk to a voice agent
Talk to a voice agent:

```sh
assembly agent
```

Scaffold a starter app:

# Scaffold a starter app
```sh
assembly init
```

### Quick examples

Just the text:

```sh
# Just the text, or captions
assembly transcribe call.mp3 -o text
```

Or captions:

```sh
assembly transcribe video.mp4 -o srt
```

Speaker labels + summary, as JSON:

# Speaker labels + summary, as JSON
```sh
assembly transcribe call.mp3 --speaker-labels --summarization --json
```

# Batch: a whole directory or glob, resumable on re-run
Batch: a whole directory or glob, resumable on re-run:

```sh
assembly transcribe ./recordings
```

Or pipe paths in:

```sh
find . -name "*.wav" | assembly transcribe --from-stdin
```

# Pipe audio in, pipe text out
Pipe audio in, pipe text out:

```sh
ffmpeg -i talk.mp4 -f wav - | assembly transcribe -
```

Prompt the LLM Gateway over any text:

```sh
git log --oneline -30 | assembly llm "write release notes grouped by feature/fix"
```

# Print the equivalent Python SDK script instead of running
Print the equivalent Python SDK script instead of running:

```sh
assembly transcribe --sample --speaker-labels --show-code
```

Expand All @@ -123,10 +173,22 @@ assembly transcribe --sample --speaker-labels --show-code

This project uses [uv](https://docs.astral.sh/uv/):

Create/refresh the venv:

```sh
uv sync
```

Run the CLI from the locked environment:

```sh
uv run assembly --help
```

Run the full gate CI runs:

```sh
uv sync # create/refresh the venv
uv run assembly --help # run the CLI from the locked environment
./scripts/check.sh # the full gate CI runs
./scripts/check.sh
```

See [AGENTS.md](AGENTS.md) for development conventions and architecture notes.
Expand Down
Loading