Skip to content
Agents tracked: 492 Releases (7d): 545 Agent status: 1 with issuesSince last limit reset: Claude 9d · Codex 7d For AI agents: Markdown Updated Nov 20, 2026

Pipecat by Daily

An open-source Python framework for voice and multimodal conversational agents, maintained by Daily and the community.

AI voice agents Voice agent frameworkOpen source · BSD-2-ClauseFree to start

Use it in: API / SDK

Price
Free (OSS)
free and open source
Popularity
#5 in Voice
Gid Score 47 / 100 · #52 of 251 ranked AI agents
Trend
Growing fast
downloads up 40.0% over 30 days · up 6.0% last week
Development
Actively updated
latest 1.16.0, 8d ago
Community
17.3K GitHub stars
391K package downloads a week

Usage data: latest readings Nov 17 to Nov 19, 2026, last checked Nov 19, 06:26 UTC. Date of each number

What Pipecat does

Pipecat is a voice agent framework from Daily, first released in May 2024. You use it through a Python library. It is free and open source (BSD-2-Clause); you pay only for the models it calls.

Key facts

MakerDaily
TypeVoice agent framework
First releasedMay 2024
LicenseBSD-2-Clause
InterfacesPython library
Main languagePython
Open issues and PRs511

Pricing

Pipecat is open source and free to use; you pay only for the models and infrastructure it runs on.

Checked Nov 4, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

What's new in Pipecat: September 2026

Full monthly summary

September brought expanded speech and text service capabilities across multiple providers, improved latency visibility and eval testing, and support for newer SDK versions. The month focused on fine-grained control over transcription, synthesis quality, and evaluation tools.

Action needed: SpeechmaticsSTTService now targets Speechmatics Agent STT (/v2/agent) and requires the speechmatics-agent-stt SDK instead of speechmatics-voice.
  • Latency breakdown now shows the timeline of where delays occur in user-to-bot exchanges.
  • Evaluation scenarios can now play audio files as user input instead of synthesizing text.
  • Multiple speech services gained new configuration options: Azure STT silence timeout, DeepgramFlux profanity filtering, OpenAI transcription keywords, and voice effect controls.
  • SpeechmaticsSTTService now reconnects with exponential backoff and buffering on connection failures.

4 releases this month · summarised from the official release notes · all months

AgentGid articles about Pipecat

All guides

Get started with Pipecat

PyPIpip install pipecat-ai

These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.

Compare Pipecat with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
9 692/4 3M up 4.1% up 37.8% — — Free + $0.08/extra minute
29
542/4 809K up 13.0% up 39.5% — — Free + $0.055/min
36 52 1.2M down 3.5% up 22.4% 15.3K+14/day 1.8.132d ago Free (OSS)
37
VapiVapi, Inc.
522/4 645K up 1.7% up 26.3% — — Free + $0.05/min
—
— — — — — — Free + $0.14/min
—
SynthflowSynthflow AI
— — — — — — Custom

Head to head: Pipecat vs ElevenLabs Agents · Pipecat vs Retell AI · Pipecat vs LiveKit Agents · Pipecat vs Vapi

Tools used with Pipecat

All tools

What 118 public GitHub projects that depend on Pipecat use with it, from their dependency files.

  1. python-dotenv87.3%
  2. FastAPI65.3%
  3. Uvicorn63.6%
  4. Loguru39.8%
  5. NumPy28.8%
  6. aiohttp24.6%
  7. OpenAI Python Library23.7%
  8. Pydantic22.9%
  9. websockets21.2%
  10. pytest19.5%

Used far more often here than in AI-built projects overall: what sets Pipecat projects apart.

  1. Deepgram SDK (Python)11.0% · 689.0×
  2. LiveKit API4.2% · 265.0×
  3. aiortc5.9% · 185.5×
  4. kokoro-onnx5.1% · 63.6×
  5. Twilio13.6% · 60.6×
  6. PyAudio10.2% · 57.8×
  7. ElevenLabs (Python)4.2% · 37.9×
  8. Faster Whisper10.2% · 31.8×

Ratings from people who use Pipecat

No ratings yet. Used Pipecat? Rate it and say what it is good and bad at.

Pipecat news

All AI agent news

  1. Release GitHub Releases

    Pipecat 1.16.0 released

    Added a normalization field to CartesiaTTSService.Settings and CartesiaHttpTTSService.Settings, passing Cartesia's text normalization mode ("auto", "off", or a locale code such as "en-GB") through…; Added SarvamHttpSTTService, which sends each VAD speech…

What changed: recent Pipecat releases

10 stable releases in the last 90 days · Monthly summary · Full changelog

1.16.0
  • Added a normalization field to CartesiaTTSService.Settings and CartesiaHttpTTSService.Settings, passing Cartesia's text normalization mode ("auto", "off", or a locale code such as "en-GB") through…
  • Added SarvamHttpSTTService, which sends each VAD speech segment to Sarvam's REST speech-to-text API (saaras:v4 by default, or saaras:v3) and yields the transcription from run_stt().
  • Added max_speakers and filter_profanity to AssemblyAISTTService.Settings, passing AssemblyAI's speaker-label cap and profanity filter through to the streaming session.
  • CartesiaSTTService.Settings now exposes Cartesia's min_volume and max_silence_duration_secs, which control the silence that triggers automatic transcript finalization on ink-whisper models.
  • Added speed to Inworld Realtime's AudioOutput, so a session can set the agent's speaking rate.
  • Added noise_reduction to Inworld Realtime's AudioInput, so a session can enable Inworld's near-field or far-field input filter.
1.15.0
  • Added a custom_configuration field to NvidiaTTSService.Settings, which forwards model-specific key/value parameters to NVIDIA TTS — Magpie's flush, chunk_len_threshold and max_chunk_threshold…
  • Added ClassifierUserTurnStopStrategy and ClassifierUserTurnStrategies, which let a classifier, such as JevClassifier, decide whether the user's turn is complete.
  • Added number_pronunciation_language to SmallestTTSService settings, which reads numerals, currency, times and dates in a language of its own, independent of the synthesis language.
  • Added text_matches to scripted eval expectations: one or more regular expressions the event's text must each match, such as a format a reply must open with.
  • LLMWithBackend(predictive_delegation=PredictiveDelegation(classifier)) is an optimization that can speed up responses that need backend involvement.
  • Added AICTytoObserver, which scores the quality of the user's audio with the ai-coustics Tyto model after every 5 seconds of received audio.
Earlier releases
1.14.0
  • Added PerplexityAgentHttpLLMService for Perplexity's Agent API, which answers with web search and supports function calling. It defaults to openai/gpt-5.6-luna with web search on.
  • Settings adds preset, web_search and max_steps. preset and model are independent, and at least one must be set.
  • With neither preset nor reasoning set, each request sends Perplexity's fast preset, its lowest-latency setup, and the first request for each model logs it.
  • Answers can include citation markers such as [1], and Anthropic models need max_completion_tokens set.
  • NvidiaSTTService now exposes speaker diarization in transcription frames. When speaker_diarization is enabled, each contiguous speaker run of a final result is emitted as its own frame with the…
  • Added NvidiaOmniLLMService for NVIDIA Nemotron Omni models, which take speech, images, and video as well as text.
1.13.0
  • Added support for clients sending files and images to the bot via the new RTVI send-file message, incorporating them into the LLM context.
  • New frames: FileRawFrame, InputFileRawFrame, and UserFileRawFrame, carrying a file payload as inline base64 bytes or as a URL.
  • New LLMContext methods: create_file_message(), create_file_url_message(), and add_file_frame_message(), producing universal file_base64 (base64 data URL) and file_url content items translated per…
  • File URLs are resolved at the LLM service, right before each completion, because the right resolution depends on the provider: each adapter declares which URLs its provider can consume directly…
  • FileResolver is configured per LLM service via the new file_resolver parameter. It downloads http(s) URLs only when the resolved address is publicly routable or falls within its…
  • New FileStorage interface (pipecat.utils.file_storage) with a LocalFileStorage default implementation. save() returns a URL the backend can later resolve (pipecat:<id> for local storage).
1.12.0
  • TTS sentence aggregation follows Settings.language, defaulting to English when unspecified. Language updates apply with TTS settings.
  • Added TTSService.pronunciation_transform_ipa(), which builds a text transform from a word-to-IPA mapping so a voice says names and terms it would otherwise guess from spelling.
  • Added client-mode reconnect to MOQTransport: when the relay session drops, the transport redials with backoff for as long as MOQParams.connection_timeout allows the client to be missing, keeps its…
  • Added MOQRunnerArguments.relay_url for dialing a relay by its full URL, query string included.
  • 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.
1.11.0
  • Added BaseAudioResampler.flush() and BaseAudioResampler.reset(), so callers can mark stream boundaries themselves rather than relying on SOXRStreamAudioResampler's inactivity timeout.
  • Scripted eval expectations on function_call 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 partial_results_stability, 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 (eq_car, eq_telecomhp8k) through to the synthesis request.
  • Added a reasoning_effort field to GroqLLMService.Settings, which passes Groq's reasoning effort control through to the completion request.
  • 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, xhigh).

Pipecat popularity and usage data

Pipecat was downloaded 391K times from PyPI in the week ending Nov 17, 2026, up 6.0% on the week before and up 40.0% over the last 30 days compared with the 30 before. The GitHub repository has 17.3K stars, 715 of them added in the last 30 days. The latest stable release is 1.16.0, published Nov 12, 2026; there were 3 stable releases in the past 30 days. It was mentioned in 2 Hacker News posts and comments over the last 30 days.

Downloads per dayPyPI, 7-day average 55.8K/day
GitHub starsrunning total 17.3K
Hacker News mentionsposts and comments, rolling 7-day total 0 this week

Download the raw daily series: pipecat.csv

Gid Score breakdown

Adoption58
Community52
Attention0
Momentum70

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
Package downloadsNov 17, 2026Nov 19, 06:24 UTC
GitHub starsNov 19, 2026Nov 19, 06:26 UTC
Hacker News mentionsNov 18, 2026Nov 19, 06:26 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

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 391K times from PyPI in the week ending Nov 17, 2026, up 6.0% on the week before and up 40.0% over the last 30 days compared with the 30 before. The GitHub repository has 17.3K stars, 715 of them added in the last 30 days. The latest stable release is 1.16.0, published Nov 12, 2026; there were 3 stable releases in the past 30 days.

What is the latest version of Pipecat?

The latest stable release we track is 1.16.0, published on Nov 12, 2026.

What are the alternatives to Pipecat?

The closest alternatives in the same category by Gid Score are ElevenLabs Agents, Retell AI, LiveKit Agents, Vapi.

For the makers of Pipecat badges, corrections

Add a live badge to your README or site:

AgentGid: #5 in Voice Gid Score: 47/100 downloads: 391K/week ▲40% 30d

[![AgentGid: #5 in Voice](https://agentgid.com/badges/pipecat-rank.svg)](https://agentgid.com/agents/pipecat/)
[![Gid Score: 47/100](https://agentgid.com/badges/pipecat-score.svg)](https://agentgid.com/agents/pipecat/)
[![downloads: 391K/week ▲40% 30d](https://agentgid.com/badges/pipecat-downloads.svg)](https://agentgid.com/agents/pipecat/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

PyPI: pipecat-ai. GitHub: pipecat-ai/pipecat. See data sources for how each one is collected.