or run

tessl search
Log in

Version

Workspace
tessl
Visibility
Public
Created
Last updated
Describes
pypipkg:pypi/pipecat-ai@0.0.x

docs

core-concepts.mdindex.mdpipeline.mdrunner.mdtransports.mdturns.md
tile.json

tessl/pypi-pipecat-ai

tessl install tessl/pypi-pipecat-ai@0.0.0

An open source framework for building real-time voice and multimodal conversational AI agents with support for speech-to-text, text-to-speech, LLMs, and multiple transport protocols

services-reference.mddocs/reference/

Services Reference

LLM Services (20+ Providers)

Complete Documentation: LLM Services →

OpenAI

{ .api }
from pipecat.services.openai import OpenAILLMService

llm = OpenAILLMService(
    api_key="sk-...",
    model="gpt-4",  # gpt-4, gpt-4-turbo, gpt-3.5-turbo
    base_url=None,  # Optional custom endpoint
    params={"temperature": 0.7, "max_tokens": 1000}
)

Anthropic

{ .api }
from pipecat.services.anthropic import AnthropicLLMService

llm = AnthropicLLMService(
    api_key="sk-ant-...",
    model="claude-3-5-sonnet-20241022",
    params={"temperature": 0.7, "max_tokens": 4096}
)

Google

{ .api }
from pipecat.services.google import GoogleLLMService

llm = GoogleLLMService(
    api_key="AIza...",
    model="gemini-2.0-flash-exp",
    params={"temperature": 0.9}
)

Other LLM Providers: Azure, AWS Bedrock, Groq, Ollama, Cerebras, DeepSeek, Fireworks, Together AI, Perplexity, SambaNova, OpenRouter, and more.

TTS Services (15+ Providers)

Complete Documentation: TTS Services →

OpenAI TTS

{ .api }
from pipecat.services.openai import OpenAITTSService

tts = OpenAITTSService(
    api_key="sk-...",
    voice="alloy",  # alloy, echo, fable, onyx, nova, shimmer
    model="tts-1-hd"  # tts-1 or tts-1-hd
)

ElevenLabs

{ .api }
from pipecat.services.elevenlabs import ElevenLabsTTSService

tts = ElevenLabsTTSService(
    api_key="...",
    voice_id="voice-id",
    model="eleven_turbo_v2",
    params={"stability": 0.5, "similarity_boost": 0.75}
)

Cartesia

{ .api }
from pipecat.services.cartesia import CartesiaTTSService

tts = CartesiaTTSService(
    api_key="...",
    voice_id="voice-id",
    model="sonic-english"  # Ultra-low latency
)

Other TTS Providers: PlayHT, Deepgram, Rime, Azure, Google, AWS, and more.

STT Services (10+ Providers)

Complete Documentation: STT Services →

Deepgram

{ .api }
from pipecat.services.deepgram import DeepgramSTTService

stt = DeepgramSTTService(
    api_key="...",
    model="nova-2",  # base, nova, nova-2, whisper-cloud
    language="en",
    interim_results=True,
    smart_format=True,
    vad_events=True
)

AssemblyAI

{ .api }
from pipecat.services.assemblyai import AssemblyAISTTService

stt = AssemblyAISTTService(
    api_key="...",
    sample_rate=16000,
    word_boost=["custom", "vocabulary"],
    boost_param="high"
)

Gladia

{ .api }
from pipecat.services.gladia import GladiaSTTService

stt = GladiaSTTService(
    api_key="...",
    language="en",
    sample_rate=16000
)

Other STT Providers: Azure, Google, AWS, Whisper (local), and more.

Realtime Multimodal Services

Complete Documentation: Realtime Services →

OpenAI Realtime

{ .api }
from pipecat.services.openai import OpenAIRealtimeSTTService, OpenAIRealtimeTTSService

# Combined STT+TTS with low latency
stt = OpenAIRealtimeSTTService(api_key="...")
tts = OpenAIRealtimeTTSService(api_key="...")

Gemini Live

{ .api }
from pipecat.services.google import GeminiLiveService

service = GeminiLiveService(
    api_key="...",
    model="gemini-2.0-flash-exp"
)

Vision and Image Services

Complete Documentation: Vision Services →

Moondream

{ .api }
from pipecat.services.moondream import MoondreamService

vision = MoondreamService()

DALL-E

{ .api }
from pipecat.services.openai import OpenAIImageGenService

image_gen = OpenAIImageGenService(
    api_key="...",
    model="dall-e-3",
    params={"size": "1024x1024", "quality": "hd"}
)

Service Features Comparison

FeatureOpenAIAnthropicGoogleDeepgramElevenLabs
LLM--
TTS-
STT✓ Realtime--
Vision--
Function Calling--
Streaming
Realtime-✓ Live--

Installation by Service

# LLM providers
pip install "pipecat-ai[openai]"      # OpenAI
pip install "pipecat-ai[anthropic]"   # Anthropic
pip install "pipecat-ai[google]"      # Google
pip install "pipecat-ai[azure]"       # Azure
pip install "pipecat-ai[aws]"         # AWS Bedrock

# TTS providers
pip install "pipecat-ai[elevenlabs]"  # ElevenLabs
pip install "pipecat-ai[cartesia]"    # Cartesia
pip install "pipecat-ai[playht]"      # PlayHT

# STT providers
pip install "pipecat-ai[deepgram]"    # Deepgram
pip install "pipecat-ai[assemblyai]"  # AssemblyAI
pip install "pipecat-ai[gladia]"      # Gladia

# Transports
pip install "pipecat-ai[daily]"       # Daily.co
pip install "pipecat-ai[livekit]"     # LiveKit

# Everything
pip install "pipecat-ai[all]"

See Also