Tag
Voice & audio tools
Speech, TTS, realtime voice. 10 reviewed tools: 10 free or open source.
Order: free and open source first, then hosted products with a real free tier, then paid-led; catalog order inside each group, with quiet or archived repos last. Not a score, and no tool pays for its place.
10 tools
- LiveKitApache-2.0 realtime rooms, SFU, and agents
Free / OSS · Apache-2.0 · 21.6k GitHub stars
VerdictApache-2.0 voice/video/agent runtime. Self-host is the free path; Cloud pricing is not confirmed here.
CatchSelf-hosting an SFU is ops-heavy. Cloud Build pricing and free allowances are not confirmed here; check the vendor site. Do not assume Cloud is free.
- Tone.jsMIT Web Audio: synths, Transport, effects, sample-accurate
Free / OSS · OSS/MIT · 14.8k GitHub stars
VerdictMIT musical Web Audio for composition, not sprite playback.
CatchSynths/Transport/effects/sample-accurate scheduling — not audio-sprite playback. W4 cut re-opened.
- PipecatBSD-2 voice and multimodal realtime agents (Daily)
Free / OSS · BSD-2-Clause · 16.6k GitHub stars
VerdictBSD-2 realtime voice-agent framework. Pipelines you own; media/model meters separate.
CatchVs LiveKit Agents (already covered under LiveKit comms stack) and OpenAI Realtime / voice extras: Pipecat is the pipeline framework for voice agents, not the SFU product. Daily transport/cloud and third-party STT/TTS meters when you leave local mocks. Not a text-only MCP orchestrator.
- VoiceboxLocal-first OSS voice studio — clone, TTS, dictate, MCP voice for agents
Free / OSS · OSS/MIT · 58k GitHub stars
VerdictMIT local voice studio. Install when agents and humans need on-device TTS/STT without a cloud voice vendor.
CatchLocal GPU/CPU and model downloads are on you; macOS/Windows desktop footprint is heavier than a REST TTS call. Large open-issue count — treat cutting-edge engines as experimental. Vs ElevenLabs-class cloud TTS (paid APIs) and Whisper-only STT stacks: Voicebox owns both ends of the loop locally, with agent voice as a first-class surface.
- UnmuteOne voice-agent spec compiled to LiveKit, Pipecat, or SLNG
Free / OSS · OSS/MIT · 27 GitHub stars
VerdictMIT voice-agent spec compiler. Write once when you refuse to rewrite the agent for each voice runtime.
CatchVs Voicebox (local TTS/STT studio) and raw LiveKit/Pipecat apps: Unmute is the compile-from-spec layer, not the voice models and not a single runtime. Young project; you still operate the chosen target stack and vendor credentials behind the compile.
- llama-swapMIT one-binary proxy that hot-swaps local models on demand
Free / OSS · OSS/MIT · 6k GitHub stars
VerdictMIT local-model switchboard when agents need many llama.cpp/vLLM models behind one endpoint on limited VRAM — skip if Ollama alone covers your models.
CatchIt is a process manager and proxy, not an inference engine — you still configure each upstream server, and a swap means a cold model load (seconds to minutes on big GGUFs). Config is the product: wrong `cmd` flags fail per model. Vs ollama (bundled runtime + model registry) and vllm (serving engine): llama-swap is the switchboard in front of whatever runtimes you already trust.
- HandyMIT offline push-to-talk dictation for any text field — Whisper or Parakeet, nothing leaves your machine
Free / OSS · OSS/MIT · 34.1k GitHub stars
VerdictThe free, private way to talk to your coding agents instead of typing — great on Mac and Windows, more setup on Wayland.
CatchNeeds microphone and accessibility permissions to paste into other apps. Linux on Wayland is the weak spot: global shortcuts have to be set up in your desktop environment and text input needs wtype, dotool or ydotool. Larger Whisper models want a decent GPU; on a laptop CPU stick to Parakeet. Transcription only — no text-to-speech or voice cloning. Vs voicebox (local voice studio with TTS, cloning and MCP voice hooks): Handy is the small, dictation-only tool.
- Kitten TTSApache-2.0 Python TTS library that runs on a CPU
Free / OSS · Apache-2.0 · 16.2k GitHub stars
VerdictA strong local TTS default for agents and apps — use the Apache-2.0 ONNX models if the KittenTTS 2 license is a problem for you.
CatchThe weights are licensed separately from the code. KittenTTS 2 uses the Stellon Labs Community License: free for research and non-commercial use, and for commercial use only until you or your affiliates pass USD 1M in annual revenue or total funding. The small 0.8 ONNX models are Apache-2.0. KittenTTS 2 wants about 6 GB of RAM on CPU or about 8 GB on a GPU, emotion control is beta, and only clone voices you have consent to use.
- LocalAIMIT self-hosted OpenAI-compatible engine for any model
Free / OSS · OSS/MIT · 49.6k GitHub stars
VerdictThe broadest self-hosted, OpenAI-compatible model server.
CatchIt gained about 265 stars a week over 3.5 years, but it is a long-running, real project, not a hype spike. Performance depends on your hardware and the backend you choose, and configuring models takes more work than Ollama.
- ComfyUIGPL-3.0 node-graph engine and API for local image, video and audio models
Free / OSS · GPL-3.0 · 139k GitHub stars
VerdictThe default local engine for generative media pipelines — keep custom nodes to ones you trust.
CatchIt is an engine you operate, not a one-click generator: node graphs have a learning curve, and the large custom-node ecosystem is third-party Python you are running with full access to your machine, so vet what you install. Real speed needs a decent GPU. Comfy Cloud and the partner nodes for closed models are paid; the local engine is free. GPL-3.0 matters if you plan to redistribute a modified build.
FAQ
- What is the top free pick among Voice & audio tools?
- LiveKit leads the Stack Gems list for Voice & audio tools. Verdict: Apache-2.0 voice/video/agent runtime. Self-host is the free path; Cloud pricing is not confirmed here.
- How many Voice & audio tools does Stack Gems review?
- 10: 10 free or open source. Each review has a verdict and an honest Catch; no tool pays for its spot.
- Which Voice & audio tools can I self-host for free?
- LiveKit, Tone.js, Pipecat, Voicebox, Unmute, llama-swap, Handy, Kitten TTS and 2 more.
- Which Voice & audio tools have the most GitHub stars?
- ComfyUI (139k), Voicebox (58k), LocalAI (49.6k), per GitHub on 2026-10-19. Stars measure attention, not fit; read the Catch.
- What is the catch with LiveKit?
- Self-hosting an SFU is ops-heavy.