Privacy and advertising choices
Git-Stars uses essential storage for site operation. Optional analytics and ad-measurement scripts stay disabled unless you accept them; partners such as Google may then use cookies or similar identifiers where required. Privacy Policy
Build local voice agents with open-source models
This repository page has enough original analysis, source evidence, and comparison context to be treated as an indexable Git-Stars review.
100
review score
Problem solved
It solves the fragmentation of building voice agents by providing a fully integrated, swappable pipeline that works with open-source models locally or with hosted providers, avoiding vendor lock-in and enabling privacy-sensitive or offline deployments.
Deployment reality
The available setup signal starts with: pip install speech-to-speech. Treat this as a starting point, then ask Codex or Claude to inspect the README, environment variables, runtime version, and deployment target before production use.
Commercial use
The recorded license is Apache-2.0. This is a useful commercial-use signal, but teams should still verify license text, dependencies, model/API terms, and trademark constraints.
Capability ceiling
Developers can build real-time conversational voice agents, such as customer support bots, personal assistants, or interactive robots (e.g., Reachy Mini). The ceiling includes production-grade, low-latency voice interaction with custom LLMs, STT, and TTS components, all controllable via CLI and compatible with any OpenAI Realtime client.
Git-Stars is independent and not affiliated with GitHub or this project. Analysis may be AI-assisted and based on public repository metadata plus short README-derived summaries. We do not mirror full README files, docs, issues, or social comments.
huggingface/speech-to-speech is tracked as a Python project in the AI Agent, AI App, Developer Tool, UI Framework area. This evaluation combines public GitHub metadata, category signals, short source summaries, and Git-Stars editorial rules rather than copying project documentation.
Momentum check: the repository has 12k total stars, with +0 today, +0 this week, and +6.2k this month. These growth windows help distinguish durable adoption from short-lived visibility spikes.
Maintenance check: current activity is Active; the latest push was 11 days ago, and the open issue queue is 136, about 1.11% of total stars. Treat this as an adoption signal, not a substitute for engineering due diligence.
Adoption check: 1.5k forks and 12k watchers suggest how often the project is reused or followed. License signal: Apache-2.0. Always verify license compatibility before commercial or internal use.
Practical fit: this project is most relevant when you need AI prototypes, LLM workflows, and agent-style applications. Be cautious when you need a legal review, security audit, or production SLA.
Source check: Git-Stars currently has 2 explicit source reference(s) for this report and a recent growth signal of 6.2k. Follow the original GitHub repository for final install, security, and release information.
Analysis
ReadyOriginal problem, capability, and verdict guidance are available.
Sources
ReadyRepository metadata and README/source references are attached.
License
ReadyApache-2.0 is recorded for review.
Maintenance
ReadyRecent activity is visible in repository metadata.
Alternatives
ReadyEnough nearby projects exist for comparison.
Momentum
12k Stars
Reuse
1.5k Forks
Attention
12k Watchers
Maintenance
active
License
Apache-2.0
Open issues
136
A low-latency, modular voice-agent pipeline (VAD -> STT -> LLM -> TTS) that exposes an OpenAI Realtime-compatible WebSocket API. Every component is swappable, supporting local and hosted models.
Key Features
- Fully modular pipeline: VAD, STT, LLM, TTS components are swappable via CLI flags. - OpenAI Realtime-compatible WebSocket API for easy client integration. - Supports multiple backends including local models (e.g., Parakeet TDT, Qwen3-TTS) and hosted providers.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
AI App
End-user AI applications and AI-native product examples
Developer Tool
Tools that improve coding, testing, build, and local workflow
UI Framework
Frontend frameworks, design systems, and interface libraries
pip install speech-to-speech80
Health Score
Active
Commit Activity
Aug 7, 2024
Created
Aug 11, 2026
Last push
+233
Today's growth
+1.3k
7-day growth
+5.0k
30-day growth
Forks
Open
Watchers
huggingface
GitHub profilecodecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
sindresorhus/awesome
😎 Awesome lists about all kinds of interesting topics
freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
EbookFoundation/free-programming-books
:books: Freely available programming books
openclaw/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
✓
License
✓
Forked
✓ Active
Maintained
Problem Solved
It solves the fragmentation of building voice agents by providing a fully integrated, swappable pipeline that works with open-source models locally or with hosted providers, avoiding vendor lock-in and enabling privacy-sensitive or offline deployments.
Capabilities
Developers can build real-time conversational voice agents, such as customer support bots, personal assistants, or interactive robots (e.g., Reachy Mini). The ceiling includes production-grade, low-latency voice interaction with custom LLMs, STT, and TTS components, all controllable via CLI and compatible with any OpenAI Realtime client.
Bottom Line
This framework is ideal for developers who want to build voice agents with full control over components and data privacy, using open-source models. It is not for those seeking a fully managed, no-code solution. The key trade-off is flexibility vs. operational complexity of self-hosting.