Pipecat (Daily)
Open-source Python framework for real-time voice + multimodal AI agents, maintained by Daily.co. Pipeline-style architecture (STT → context → LLM → TTS) wired over WebRTC. The OSS substrate that many of the voice platforms build on or compose with.
At a glance
- Type
- OSS voice-agent framework (Daily.co)
- Tier
- T1
- Section
- Voice agent platforms
- Created
- 2024 (open-sourced)
- Latest release
- Active monthly releases (PyPI: pipecat-ai)
- License
- BSD-2-Clause
- Pricing
- OSS free; runs on Daily.co Cloud or self-host
- Funding
- Maintained by Daily.co — $60M raised (parent)
Taxonomy
- storage
- kv
- retrieval
- injection
- persistence
- session
- update
- agent-controlled
- unit
- turn
- governance
- inspectable
- conflict
- stateless
When to use
Optimised for: Composing real-time voice pipelines from best-of-breed STT/LLM/TTS
Anti-fit: Framework — caller wires + hosts; not a turnkey SaaS
Pros & cons
Pros
OSS BSD-2; Daily-backed; first-class WebRTC; modular pipeline; default Python voice-agent framework.
Cons
Framework not platform — caller hosts; smaller ecosystem than JS WebRTC stacks.
Claims & capabilities
OSS BSD-2; maintained by Daily.co ($60M raised); 4k+ stars; supports OpenAI Realtime + Anthropic + many STT/TTS
Technical surface
- API surface
- Python API; WebRTC transport; HTTP + Twilio integrations
- Backend storage
- In-memory context; caller adds durability
- Deployment
- Pip self-host + Daily Cloud (managed WebRTC)
- Embedding model
- not applicable — not a memory product
- Multi-tenancy
- Per-process; Daily Cloud handles tenancy
- MCP
- Composes with MCP tools (caller-side)
- A2A
- searched not found
- OpenTelemetry
- searched not found
Similar systems
Other voice agent platforms in the catalog, ranked by inbound references.
- Cartesia Sonic T1
Cartesia's Sonic TTS — state-space-model-based voice generation, lowest published TTS latency (~40ms). Cartesia raised $64M Series A Q1 2025 (Index + Lightspeed); founded by Mamba authors. Agent platform layer ('Cartesia Line') wraps Sonic with telephony + LLM.
- Vapi T1
Voice-AI developer platform — STT + LLM + TTS pipelines wired to telephony (Twilio / SIP). Used to build outbound + inbound phone agents at scale. Raised $20M Series A from Bessemer + Y Combinator (Dec 2024) at $130M valuation; revenue reported >$10M ARR by Q1 2025.
- Bland AI T1
Voice-AI platform with custom STT + LLM + TTS stack ('the whole pipeline'). Raised $40M Series A Apr-2024 (Lightspeed + Anthology). Distinguished by 'pathway' graphs (deterministic call flows) and aggressive outbound-calling positioning.
- CallRail Conversation Intelligence T2
CallRail's AI-driven conversation intelligence layer atop their call-tracking product. Marketing-vertical voice analytics — auto-tagging, sentiment, lead scoring. CallRail is profitable / private (Sageview-backed); not a voice-agent runtime but the BI / analytics adjacent layer.
- ElevenLabs Conversational AI T1
ElevenLabs launched Conversational AI Nov-2024 — STT + LLM + their own market-leading TTS in one pipeline. Combines vendor's voice cloning + multilingual TTS strengths with hosted call orchestration. ElevenLabs raised $180M Series C Jan-2025 at $3.3B val.
- Hume EVI T1
Hume's Empathic Voice Interface (EVI) — voice agent platform with vocal-affect understanding. Hume raised $50M Series B Mar-2024 (EQT). Distinguished from pure LLM voice agents by emotion/prosody modelling; uses Hume's proprietary speech-prosody models.
Related systems
References (2)
- Anthropic Claude (foundation models) depends on at runtime — adjacent-infrastructure cell: Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) depends on at runtime — adjacent-infrastructure cell: Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS