Pipecat vs Retell AI
Pipecat (Daily) and Retell AI (Retell AI) side by side on public data, as of Oct 6, 2026.
Retell AI has 2.4x the weekly package downloads of Pipecat (617K against 260K). Over the last 30 days downloads moved -18% for Pipecat and +16% for Retell AI. Pipecat shipped 8 stable releases in the past 90 days.
Side-by-side numbers
| Metric | Pipecat | Retell AI |
|---|---|---|
| Pulse Score | 39 | 50 |
| Overall rank | #70 | #38 |
| Downloads, last 7 days | 260K | 617K |
| Downloads, 7-day change | up 8.9% | up 15.6% |
| Downloads, 30-day change | down 17.5% | up 15.8% |
| VS Code installs | — | — |
| Marketplace rating | — | — |
| GitHub stars | 16.2K | — |
| Homebrew installs, 30 days | — | — |
| Hacker News mentions, 30 days | 1 | 0 |
| Latest stable release | 1.12.0 · 10d ago | — |
| Stable releases, 90 days | 8 | |
| Terminal-Bench (best run) | — | — |
| Price | Free (OSS) | Free + $0.055/min |
| License | BSD-2-Clause | |
| First released | — | — |
| Interfaces | Python library | — |
| Models |
Trends
Pipecat
An open-source Python framework for voice and multimodal conversational agents, maintained by Daily and the community.
Pricing: Pipecat is open source and free to use; you pay only for the models and infrastructure it runs on.
Latest release 1.12.0:
- TTS sentence aggregation follows Settings.language, defaulting to English when unspecified. Language updates apply with TTS settings.
- Added TTSService.pronunciationtransformipa(), which builds a text transform from a word-to-IPA mapping so a voice says names and terms it would otherwise guess from spelling. Each matched word is…
- Added client-mode reconnect to MOQTransport: when the relay session drops, the transport redials with backoff for as long as MOQParams.connectiontimeout allows the client to be missing, keeps its…
- Added MOQRunnerArguments.relayurl for dialing a relay by its full URL, query string included. host and port are optional when it is set, and createtransport passes it through to…
Retell AI
Platform for building, testing, deploying and monitoring AI voice and chat agents, with built-in telephony, prompt and flow builders, tool calling and analytics.
Pricing: Pay-as-you-go with $10 free credit. The voice infrastructure fee is $0.055/min, with speech, model and telephony added per minute, for a stated total of $0.07–$0.31/min. Enterprise pricing is custom.