Skip to main content
Create a new Pipecat project with guided setup for bot type, transport, AI services, and deployment options. Supports both an interactive wizard and a fully non-interactive mode for automation. Usage: 
pipecat create [TARGET_DIR] [OPTIONS]
To make an existing project agent-ready (so an AI coding assistant follows Pipecat conventions and can drive pipecat create for you), see pipecat init.
Arguments:
​
TARGET_DIR
string
The exact directory to scaffold into. pipecat create . scaffolds into the current directory and pipecat create my-bot into ./my-bot, with the project name derived from the directory. Omit it to instead create a <name> subfolder under --output (or the current directory). Pass either TARGET_DIR or --output, not both.
Options:
​
--output / -o
string
Output directory where files will be saved. Defaults to current directory.
​
--name / -n
string
Project name. Providing this flag triggers non-interactive mode.
​
--bot-type / -b
string
Bot type: web or telephony. Optional — inferred from --transport when omitted (telephony if any transport is a telephony provider, otherwise web).
​
--transport / -t
string
Transport provider. Repeatable for multiple transports (e.g. -t daily -t smallwebrtc). Valid values: daily, smallwebrtc, twilio, telnyx, plivo, exotel, daily_pstn, twilio_daily_sip.
​
--mode / -m
string
Pipeline mode: cascade or realtime.
​
--stt
string
Speech-to-Text service (cascade mode). e.g. deepgram_stt, openai_stt.
​
--llm
string
Language model service (cascade mode). e.g. openai_llm, anthropic_llm.
​
--tts
string
Text-to-Speech service (cascade mode). e.g. cartesia_tts, elevenlabs_tts.
​
--realtime
string
Realtime service (realtime mode). e.g. openai_realtime, gemini_live_realtime.
​
--video
string
Video avatar service (web bots only). e.g. heygen_video, tavus_video, simli_video.
​
--client-framework
string
Client framework (web bots only): react, vanilla, or none.
​
--client-server
string
Client dev server (when using --client-framework react): vite or nextjs.
​
--daily-pstn-mode
string
Daily PSTN mode (required when transport is daily_pstn): dial-in or dial-out.
​
--twilio-daily-sip-mode
string
Twilio + Daily SIP mode (required when transport is twilio_daily_sip): dial-in or dial-out.
​
--recording / --no-recording
boolean
default:"false"
Enable audio recording.
​
--transcription / --no-transcription
boolean
default:"false"
Enable transcription logging.
​
--video-input / --no-video-input
boolean
default:"false"
Enable video input (web bots only).
​
--video-output / --no-video-output
boolean
default:"false"
Enable video output (web bots only).
​
--deploy-to-cloud / --no-deploy-to-cloud
boolean
default:"true"
Generate Pipecat Cloud deployment files (Dockerfile, pcc-deploy.toml).
​
--enable-krisp / --no-enable-krisp
boolean
default:"false"
Enable Krisp noise cancellation (requires cloud deployment).
​
--observability / --no-observability
boolean
default:"false"
Enable observability.
​
--eval / --no-eval
boolean
default:"false"
Make the generated bot eval-ready: add an eval transport entry and starter scenarios in server/evals/, plus the dependencies to run them. See the evals docs for the verification workflow.
​
--config / -c
string
Path to a JSON config file. Triggers non-interactive mode. CLI flags override file values.
​
--dry-run
boolean
default:"false"
Print the resolved configuration as JSON without generating any files.
​
--list-options
boolean
default:"false"
Print all available service options as JSON and exit. Useful for CI scripts and coding agents that need to discover valid values at runtime.

​
Quickstart Project

To scaffold the canned quickstart project (sensible defaults, no prompts): 
pipecat create quickstart

​
Interactive Setup

When run without --name or --config, the CLI guides you through selecting:
  • Bot type and client framework - Phone, web (Next.js, Vite, Vanilla JS), or mobile
  • Transport provider - Daily, Twilio, Telnyx, Plivo, Exotel
  • Pipeline mode - Cascade or Realtime
  • AI services - STT, LLM, and TTS providers
  • Optional features - Additional capabilities for your bot
  • Deployment target - Local development or Pipecat Cloud

​
Non-Interactive Mode

When --name or --config is provided, all configuration is taken from CLI flags or a JSON config file with no interactive prompts. This is useful for automation, scripting, and coding agents. (When you scaffold in place with a TARGET_DIR, supplying --bot-type or --config is enough to go non-interactive — the project name is derived from the directory.) All required fields must be specified or the command exits with a list of all missing/invalid fields. Bot type is not required — it’s inferred from --transport when omitted.

​
Examples

​
Interactive Wizard

pipecat create

​
In-Place (current directory)

pipecat create . --transport daily --mode cascade \
  --stt deepgram_stt --llm openai_llm --tts cartesia_tts
Scaffolds into the current directory, deriving the project name from it. Bot type is inferred from the transport (web here), so --bot-type is optional.

​
Non-Interactive (Cascade)

pipecat create --name my-bot --bot-type web --transport daily \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts

​
Non-Interactive (Realtime)

pipecat create --name rt-bot --bot-type web --transport smallwebrtc \
  --mode realtime --realtime openai_realtime

​
Multiple Transports

pipecat create --name my-bot --bot-type web \
  --transport daily --transport smallwebrtc \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts

​
With React Client

pipecat create --name my-bot --bot-type web --transport daily \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts \
  --client-framework react --client-server vite

​
Telephony

pipecat create --name call-bot --bot-type telephony --transport twilio \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts

​
Eval-Ready Bot

pipecat create --name my-bot --bot-type web --transport daily \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts \
  --eval

​
Discover Available Options

# List all valid service values as JSON
pipecat create --list-options
Output: 
{
  "bot_type": ["web", "telephony"],
  "transports": {
    "web": ["daily", "smallwebrtc"],
    "telephony": ["twilio", "twilio_daily_sip_dialin", "twilio_daily_sip_dialout", ...]
  },
  "stt": ["deepgram_stt", "mistral_stt", "openai_stt", "xai_stt", ...],
  "llm": ["openai_llm", "anthropic_llm", ...],
  "tts": ["cartesia_tts", "elevenlabs_tts", "soniox_tts", ...],
  "realtime": ["openai_realtime", "gemini_live_realtime", ...],
  "video": ["heygen_video", "tavus_video", "simli_video"]
}
This is useful for scripting — for example, to pick a random TTS provider: 
options=$(pipecat create --list-options)
tts=$(echo "$options" | jq -r '.tts[0]')

​
Dry Run

# Preview resolved config as JSON without generating files
pipecat create --name my-bot --bot-type web --transport daily \
  --mode cascade --stt deepgram_stt --llm openai_llm --tts cartesia_tts \
  --dry-run

​
From Config File

pipecat create --config project-config.json
Sample project-config.json: 
{
  "project_name": "my-bot",
  "bot_type": "web",
  "transports": ["daily"],
  "mode": "cascade",
  "stt_service": "deepgram_stt",
  "llm_service": "openai_llm",
  "tts_service": "cartesia_tts",
  "recording": false,
  "transcription": false,
  "deploy_to_cloud": true,
  "enable_krisp": false,
  "enable_observability": false
}
CLI flags override any values in the file, so you can use a base config and customize per-run: 
pipecat create --config base-config.json --name custom-name --no-deploy-to-cloud

​
Specify Output Directory

pipecat create --output my-bot

​
Generated Project Structure

mybot/
├── server/                 # Python bot server
│   ├── bot.py              # Main bot implementation
│   ├── evals/              # Starter eval scenarios (with --eval)
│   ├── pyproject.toml      # Python dependencies
│   ├── .env.example        # Environment variables template
│   ├── Dockerfile          # Container image (if cloud enabled)
│   └── pcc-deploy.toml     # Deployment config (if cloud enabled)
├── client/                 # Web client (if generated)
│   ├── src/
│   ├── package.json
│   └── ...
├── .gitignore
└── README.md               # Project setup instructions