All tasks / Tools
Pipecat
Open-source Python framework for real-time voice and multimodal agents that plugs in STT, LLM, TTS and speech-to-speech services.
- Daily (open source)
- Local or cloud
- Free, open source
Where it ranks
- –Voice agentsFrameworks · Local · no rated model available here yetWith cloud models: tier B (63.4% on Cekura Bench: voice agent platforms (workflow benchmark v1))
Ranked by its own benchmark result where it has one; otherwise by the best model it offers.
Facts
- Vendor
- Daily (open source)
- Approach
- Frameworks
- Where it runs
- Runs fully on your hardware with local models; cloud models optional
- Interface
- API
- Skill level
- Advanced: command line, node graphs or self-hosting
- Price
- Free, open source
- Pricing notes
- Free and open source (BSD-2-Clause); speech-to-speech integrations include OpenAI Realtime, Gemini Live, Grok Voice Agent and AWS Nova Sonic; local Whisper and Kokoro services available.
- Source code
- Open source (BSD-2-Clause)
- GitHub stars
- 16.6k (18 Oct 2026)
- Last verified
- 18 Oct 2026
Price from github.com, 18 Oct 2026.
Models it gives you
- SGemini 3.8 LiveGoogle · closed
- SGrok Voice 3.0xAI · closed
- BGPT-Realtime-2.1OpenAI · closed
- CGPT-Realtime-2.1 MiniOpenAI · closed
- –Nova 2.5 SonicAmazon · closed
- –Whisper large-v3OpenAI · open weights
- –Kokoro-82M v1.0hexgrad · open weights
Its own benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Cekura Bench: voice agent platforms (workflow benchmark v1) | 63.4% | PipecatSubmitted Pipecat bot (cascade with OpenAI Responses LLM); frozen v1 release. | 12 Oct 2026 | benchmarks.cekura.ai |