- 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…
- Added interruptible to every frame: True by default and False by default for UninterruptibleFrame subclasses, and what the frame queue, the processor's interruption handling and the speculation…
- JudgeVerdict now has a confidence, from 0 to 1, saying how sure the judge is. With Jev the number is calibrated. With an LLM it is the LLM's own guess.
Pipecat by Daily
Pulse Score
39 / 100
Rank #70 of 157
Downloads, last 7 days
260K
up 8.9% vs previous week
Downloads, last 30 days
1M
down 17.5% vs previous 30 days
GitHub stars
16.2K
about +38 a day
Latest release
1.12.0
10d ago · 4 in 30 days
Price
Free (OSS)
checked Oct 5, 2026
Overview
An open-source Python framework for voice and multimodal conversational agents, maintained by Daily and the community.
Pipecat was downloaded 260K times from PyPI in the week ending Oct 4, 2026, up 8.9% on the week before and down 17.5% over the last 30 days compared with the 30 before. The GitHub repository has 16.2K stars, 967 of them added in the last 30 days. The latest stable release is 1.12.0, published Sep 26, 2026; there were 4 stable releases in the past 30 days. It was mentioned in 1 Hacker News posts and comments over the last 30 days.
Pipecat usage and attention over time
Download the raw daily series: pipecat.csv
Install Pipecat
| PyPI | pip install pipecat-ai |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
Key facts
| Maker | Daily |
|---|---|
| Type | Voice agent framework |
| License | BSD-2-Clause |
| Interfaces | Python library |
| Main language | Python |
| Open issues and PRs | 382 |
Pricing
Pipecat is open source and free to use; you pay only for the models and infrastructure it runs on.
, checked Oct 5, 2026. Prices change often; confirm before you buy.
Pulse Score breakdown
Adoption54
Community50
Attention0
Momentum32
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
What changed: recent Pipecat releases
8 stable releases in the last 90 days · Full changelog
- Added BaseAudioResampler.flush() and BaseAudioResampler.reset(), so callers can mark stream boundaries themselves rather than relying on SOXRStreamAudioResampler's inactivity timeout. flush()…
- Scripted eval expectations on functioncall accept an eval:: each matched call is judged by name and arguments, under a judge prompt of its own, so a scenario can check what args: cannot match…
- AWSTranscribeSTTService.Settings gained partialresultsstability, which selects AWS Transcribe's "high", "medium" or "low" interim-result stability. It still defaults to "high".
- Added an effect setting to AzureTTSService and AzureHttpTTSService, which passes Azure's <voice effect> audio effect processor (eqcar, eqtelecomhp8k) through to the synthesis request.
- Added a reasoningeffort field to GroqLLMService.Settings, which passes Groq's reasoning effort control through to the completion request. Accepted values vary by model: "low", "medium" and "high"…
- Added a delay field to OpenAIRealtimeSTTService.Settings, OpenAI's latency-versus-accuracy control for how long the model waits before emitting transcription text (minimal, low, medium, high,…
- SmallestTTSService now uses Smallest AI's continuation API: text fragments within the same LLM turn share a contextid so the server joins them into one continuous generation instead of resetting…
- Added LiveKitParams.audiooutqueuesizems to configure the outgoing rtc.AudioSource buffer size. Defaults to LiveKit's 1000 ms, so existing behaviour is unchanged.
- Added enableturndetection to GradiumSTTService. With it on, Gradium's server-side end-pointing signal decides when user turns start and end instead of the pipeline's VAD, and the service…
- ⚠️ Behavior change: Pipecat now supports the openai 3 SDK, and the openai dependency is widened to >=1.74.0,<4, so a fresh resolve picks openai 3. It builds its HTTP clients on httpx2 instead of…
- Widened the anthropic dependency to >=0.49.0,<2 to support the anthropic 1 SDK. AnthropicLLMService sends temperature, topk and topp through the request's extrabody, since the Messages API methods…
- Widened the mcp dependency to mcp[cli]>=1.24.0,<3 so MCPClient works with the MCP SDK's 2.x line as well as 1.x. The floor moves to 1.24.0, the first release carrying the streamablehttpclient…
- Added LatencyBreakdown.contributions, a timeline of the user-to-bot interval whose durations sum to the measured latency. It names the time no service reports — VAD silence, turn detection,…
- Eval scenario turns can play an audio file as the user instead of synthesizing text. A turn's audio: names a recording, resolved relative to the scenario file, in any format soundfile reads (WAV,…
- Added a cancellablebyllm argument to LLMSwitcher.registerfunction(), which forwards it to every LLM the switcher fronts. Tools registered through a switcher can now opt into LLM-side cancellation,…
- Added AssemblyAISyncSTTService, a segmented speech-to-text service backed by AssemblyAI's Sync API: pipeline VAD segments the audio and each segment (up to 120 seconds) is transcribed in one HTTP…
- AzureSTTService.Settings gained segmentationsilencetimeoutms, which sets how much silence (100–5000 ms) Azure allows inside a phrase before it emits a final transcript. Azure's default of 500 ms…
- Added onprogress and onupdate event handlers to the eval framework. EvalSession and EvalSuite are now BaseObjects, so eval progress is observed the same way as every other Pipecat event.…
- A directory passed to pipecat eval run now reads .yml files as well as its .yaml ones, matching the scenario names a manifest resolves. A directory holding neither is still an error rather than an…
- Fixed pipecat init repeatedly offering to build a Context Hub index that already exists, and the stale-index warning never appearing, on any index refreshed by Context Hub v0.5.3 or later. A…
- Added imageurl support for Gemini adapter, enabling external URLs via Part.fromuri().
- Added Google Speech-to-Text v2 adaptation support to GoogleSTTService, so recognition can be biased toward domain terms using inline or referenced phrase sets. Configurable at construction and…
- Added MCPClient(toolsarguments=...), which injects extra arguments into every call of a tool. Use it for arguments the model shouldn't choose — a fixed search mode, an account id, a…
- Added MCPClient.tools(): LLMContext(tools=await mcp.tools()) is now all you need to use MCP tools — connecting, tool registration, and closing the connection at pipeline end are automatic.
- Added KeenableWebSearch (pipecat.services.keenable.search), an optional service that gives voice agents live web search and page reading via a hosted MCP server powered by Keenable AI. It exposes…
- Added the Pipecat Context Hub to the cli extra, so uv tool install "pipecat-ai[cli]" provides pipecat context-hub (alias pipecat ch) with no separate install — the guides pipecat init writes tell…
Pipecat alternatives
| # | Agent | Pulse | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | Last 90 days | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 18 |
ElevenLabs AgentsElevenLabs |
59 | 2.2M | up 4.2% | up 30.8% | — | — | — | Free + $0.08/extra minute | ||
| 38 |
Retell AIRetell AI |
50 | 617K | up 15.6% | up 15.8% | — | — | — | Free + $0.055/min | ||
| 39 |
LiveKit AgentsLiveKit |
50 | 988K | up 12.9% | — | — | 14.6K+33/day | 1.8.45d ago | Free (OSS) | ||
| 41 |
VapiVapi, Inc. |
50 | 570K | up 19.8% | up 13.1% | — | — | — | Free + $0.05/min | ||
| 129 |
SynthflowSynthflow AI |
16 | — | — | — | — | — | — | Custom | — | |
| 136 |
Bland AIBland |
12 | — | — | — | — | — | — | Free + $0.14/min | ||
| No agents match that filter. | |||||||||||
Head to head: Pipecat vs ElevenLabs Agents · Pipecat vs Retell AI · Pipecat vs LiveKit Agents · Pipecat vs Vapi
Pipecat FAQ
How much does Pipecat cost?
Pipecat is open source and free to use; you pay only for the models and infrastructure it runs on.
Is Pipecat open source?
Yes. Pipecat is open source, released under the BSD-2-Clause license.
How popular is Pipecat?
Pipecat was downloaded 260K times from PyPI in the week ending Oct 4, 2026, up 8.9% on the week before and down 17.5% over the last 30 days compared with the 30 before. The GitHub repository has 16.2K stars, 967 of them added in the last 30 days. The latest stable release is 1.12.0, published Sep 26, 2026; there were 4 stable releases in the past 30 days.
What is the latest version of Pipecat?
The latest stable release we track is 1.12.0, published on Sep 26, 2026.
What are the alternatives to Pipecat?
The closest alternatives in the same category by Pulse Score are ElevenLabs Agents, Retell AI, LiveKit Agents, Vapi.
Where these numbers come from
PyPI: pipecat-ai. GitHub: pipecat-ai/pipecat. See data sources for how each one is collected.