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.
Active · Verified 2026-10-26 · fresh as of 2026-10-26 · 53 cited facts, 2 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- OSS voice-agent framework (Daily.co) vendor fix
- Tier
- T1
- Section
- Voice agent platforms
- Created
- 2024 (open-sourced) repo fix
- Latest release
- v1.7.0 (2026-08-01) repo fix
- License
- BSD-2-Clause repo fix
- Pricing
- OSS free; runs on Daily.co Cloud or self-host repo fix
- Funding
- Maintained by Daily.co — $60M raised (parent) third-party fix
- Freshness
- 2026-10-26 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- kotlin, python, swift, typescript repo fix
- Protocols
- mcp-client, mcp-server, opentelemetry vendor fix
- Compliance
- ccpa, gdpr, hipaa, soc2-type2 vendor fix
- Developer activity
- OpenRank 35.85 (12-mo avg 38.12) · 132 participants — 2026-09 third-party fix
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); 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
- Both (self-hosted + managed cloud) — pip self-host + Pipecat Cloud
- 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
Compare Pipecat (Daily) with…
Alternatives to Pipecat (Daily) → live options ranked by shared design, licence, hosting and MCP support
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.
- LiveKit Agents T1
LiveKit Agents — agent framework built on LiveKit's open-source WebRTC media server. LiveKit raised $45M Series B Sep-2024 ($300M val). Powers OpenAI Realtime API's WebRTC transport (LiveKit is the substrate OpenAI chose). Agents framework formally launched 2024.
- ElevenLabs Conversational AI (now ElevenAgents) 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. As of 2026-10 ElevenLabs markets the platform as ElevenAgents.
- OpenAI Realtime API T1
OpenAI's Realtime API for native speech-to-speech multimodal interaction with GPT-4o — launched Oct 2024 (DevDay). Skips the STT → LLM → TTS pipeline by passing speech directly to GPT-4o. The platform substrate that Vapi/Retell/Bland integrate as one of their LLM choices.
- Hume EVI T1
Hume's Empathic Voice Interface (EVI) — voice agent platform with vocal-affect understanding, using Hume's proprietary speech-prosody models. Hume will shut down the EVI and TTS APIs on 2026-11-13 (announced in its docs). Hume raised $50M Series B Mar-2024 (EQT).
- Speechmatics Flow T2
Speechmatics (UK; STT leader) launched Flow Q4 2024 — conversational voice-agent platform composed on Speechmatics STT + caller LLM. Speechmatics raised $62M Series B (2022); enterprise + media customers. UK / EU data-residency lead. As of 2026-10 the Flow pages and docs redirect to Agent STT, a speech-to-text API for voice agents (Linden model, from $0.30/hour) used via LiveKit, Pipecat or the API; Flow itself is no longer listed.
Sources (52 cited facts, 2 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is OSS voice-agent framework (Daily.co) vendor
- What it does & what's distinct Open-source Python framework for real-time voice + multimodal AI agents, maintained by D… vendor
- Claims / benefits OSS BSD-2; maintained by Daily.co ($60M raised); supports OpenAI Realtime + Anthropic + … repo
- Modalities voice + text + video (WebRTC) vendor
- Created 2024 (open-sourced) repo
- Latest release v1.7.0 (2026-08-01) repo
- License BSD-2-Clause repo
- GitHub pipecat-ai/pipecat — ~16.8k stars, last commit 2026-08+ repo
- Mindshare Default voice-agent framework for Python; Daily distribution; growing OSS following vendor
- Funding Maintained by Daily.co — $60M raised (parent) third-party
- Customers / scale OSS users + Daily.co Cloud customers; case studies in vertical voice apps vendor
- Pricing OSS free; runs on Daily.co Cloud or self-host repo
- Compliance Daily.co SOC 2 / HIPAA (cloud parent) vendor
- Data handling OSS = your infra; Daily Cloud per its policy vendor
- Deployment Both (self-hosted + managed cloud) — pip self-host + Pipecat Cloud repo
- HQ US (Daily, San Francisco) vendor
- Founders / pedigree Daily.co — Kwindla Hultman Kramer (CTO); Pipecat lead = Daily team vendor
- Performance Sub-1s turn latency typical; depends on pipeline composition vendor
- Code/weights release OSS BSD-2 — github.com/pipecat-ai/pipecat repo
- API surface Python API; WebRTC transport; HTTP + Twilio integrations vendor
- Latency p50/p99 Sub-1s typical pipeline vendor
- Backend storage In-memory context; caller adds durability vendor
- Multi-tenancy Per-process; Daily Cloud handles tenancy vendor
- Encryption TLS / DTLS-SRTP for WebRTC vendor
- SSO / RBAC via Daily Cloud (Enterprise) vendor
- Versioning Pipelines versioned in caller repo repo
- Namespace primitives per-pipeline / per-session vendor
- MCP support Composes with MCP tools (caller-side) vendor
- Import / export Pipelines = Python code (portable) vendor
- Validated verticals telephony agents, in-browser voice UX, education, customer support vendor
- Time to running <1hr (pip install + provider keys) repo
- Anti-fit Framework — caller wires + hosts; not a turnkey SaaS vendor
- Optimised for Composing real-time voice pipelines from best-of-breed STT/LLM/TTS vendor
- Adjacent infrastructure Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS vendor
- Pros OSS BSD-2; Daily-backed; first-class WebRTC; modular pipeline; default Python voice-agen… vendor
- Cons Framework not platform — caller hosts; smaller ecosystem than JS WebRTC stacks. vendor
- Project & sources pipecat.ai; github.com/pipecat-ai/pipecat; docs.pipecat.ai vendor
- commit-trajectory [{"ym":"2026-03","cum":8805},{"ym":"2026-04","cum":9241},{"ym":"2026-05","cum":9460}] repo
- cost-input-usd-per-mtok 0 repo
- cost-output-usd-per-mtok 0 repo
- cost-tier free repo
- cost-pricing-model free-tier repo
- cost-last-verified 2026-06-29 repo
- architecture-deployment-locus hybrid vendor
- licensing-bucket open-source repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":385.64,"as_of":"2026-09","openrank_12mo":38.12,"openrank_current":35.85,"par… third-party
- compliance-certifications ccpa,gdpr,hipaa,soc2-type2 vendor
- sdk-languages kotlin,python,swift,typescript repo
- protocol-support mcp-client,mcp-server,opentelemetry vendor
- maturity ga registry
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
References (22)
- Alibaba Qwen 3 family integrates with — Pipecat docs have a Alibaba Qwen 3 family service page. (verified 2026-10-29)
- Anthropic Claude (foundation models) integrates with · depends on at runtime — adjacent-infrastructure cell: Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS
- Baseten integrates with — Pipecat docs have a Baseten service page. (verified 2026-10-29)
- Bland AI integrates with — Pipecat docs have a Bland AI service page. (verified 2026-10-29)
- Cartesia Sonic integrates with — Pipecat docs have a Cartesia Sonic service page. (verified 2026-10-29)
- DeepSeek R1 / V3 family integrates with — Pipecat docs have a DeepSeek R1 / V3 family service page. (verified 2026-10-29)
- ElevenLabs Conversational AI (now ElevenAgents) integrates with — Pipecat docs have a ElevenLabs Conversational AI service page. (verified 2026-10-29)
- Fireworks AI integrates with — Pipecat docs have a Fireworks AI service page. (verified 2026-10-29)
- Google Gemini 3 family integrates with — Pipecat docs have a Google Gemini 3 family service page. (verified 2026-10-29)
- Hume EVI integrates with — Pipecat docs have a Hume EVI service page. (verified 2026-10-29)
- Inworld AI integrates with — Pipecat docs have a Inworld AI service page. (verified 2026-10-29)
- Mem0 integrates with — Pipecat docs have a Mem0 service page. (verified 2026-10-29)
- Mistral Large 2 / Mixtral family integrates with — Pipecat docs have a Mistral Large 2 / Mixtral family service page. (verified 2026-10-29)
- MLflow integrates with — Pipecat docs have a MLflow service page. (verified 2026-10-29)
- OpenAI GPT family (GPT-5 / GPT-4o / o3 / o4) integrates with · depends on at runtime — adjacent-infrastructure cell: Daily WebRTC; OpenAI Realtime; Anthropic; Deepgram + Cartesia STT/TTS
- OpenAI Realtime API integrates with — Pipecat docs have a OpenAI Realtime API service page. (verified 2026-10-29)
- OpenInference integrates with — Pipecat docs have a OpenInference service page. (verified 2026-10-29)
- OpenRouter integrates with — Pipecat docs have a OpenRouter service page. (verified 2026-10-29)
- Replicate integrates with — Pipecat docs have a Replicate service page. (verified 2026-10-29)
- Speechmatics Flow integrates with — Pipecat docs have a Speechmatics Flow service page. (verified 2026-10-29)
- Together AI integrates with — Pipecat docs have a Together AI service page. (verified 2026-10-29)
- xAI Grok 4 integrates with — Pipecat docs have a xAI Grok 4 service page. (verified 2026-10-29)
Referenced by (6)
- Braintrust integrates with — Braintrust docs have a Pipecat (Daily) integration page. (verified 2026-10-29)
- Comet ML integrates with — Comet's Opik docs have a Pipecat (Daily) integration page. (verified 2026-10-29)
- Langfuse integrates with — Langfuse's integrations directory has a Pipecat (Daily) integration page. (verified 2026-10-29)
- LangSmith integrates with — LangSmith docs have a tracing integration page for Pipecat (Daily). (verified 2026-10-29)
- Mem0 integrates with — Mem0 docs have a Pipecat integration page (Integrate Mem0 with Pipecat for conversational memory in AI agents). (verified 2026-10-29)
- OpenInference integrates with — The OpenInference repo README lists an OpenInference instrumentation package for Pipecat (Daily). (verified 2026-10-29)