2,002 offers
Free Voice & Realtime — open-source & self-hostable
Speech, voice agents, and realtime pipelines
Scores rate free-tier value on a 1–10 scale. How scores work →
-
whisper.cpp Voice & Realtime 8.1 Port of OpenAI's Whisper model in C/C++ 51.3k★554/90d43 devs/90d -
NVIDIA NeMo Voice & Realtime 7.8 A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech) 17.7k★145/90d30 devs/90d -
FunASR Voice & Realtime 7.6 Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API. 18.8k★355/90d4 devs/90d -
Pipecat Voice & Realtime 7.5 Open Source framework for voice and multimodal conversational AI 13.2k★1.7k/90d11 devs/90d -
LiveKit Agents Voice & Realtime 7.5 A framework for building realtime voice AI agents 🤖🎙️📹 11.2k★489/90d39 devs/90d -
sherpa-onnx Voice & Realtime 7.1 Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages 13.4k★109/90d22 devs/90d -
GPT-SoVITS Voice & Realtime 6.9 1 min voice data can also be used to train a good TTS model! (few shot voice cloning) 59.4k★14/90d8 devs/90d -
VibeVoice Voice & Realtime 6.7 Open-Source Frontier Voice AI 49.9k★30/90d9 devs/90d -
Moonshine Voice & Realtime 6.7 Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces 8.6k★104/90d3 devs/90d -
Silero VAD Voice & Realtime 6.6 Silero VAD: pre-trained enterprise-grade Voice Activity Detector 9.5k★10/90d3 devs/90d -
HuggingFace Speech-to-Speech Voice & Realtime 6.6 Build local voice agents with open-source models 5.2k★222/90d6 devs/90d -
TEN Framework Voice & Realtime 6.5 Open-source framework for conversational voice AI agents 10.8k★33/90d10 devs/90d -
Fish-Speech Voice & Realtime 6.4 SOTA Open Source TTS 31.1k★5/90d5 devs/90d -
WhisperX Voice & Realtime 6.4 WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) 22.9k★12/90d5 devs/90d -
RealtimeSTT Voice & Realtime 6.4 A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription. 9.9k★72/90d3 devs/90d -
F5-TTS Voice & Realtime 6.3 Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching" 14.9k★9/90d4 devs/90d -
SenseVoice Voice & Realtime 6.3 Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive. 8.8k★23/90d4 devs/90d -
Chatterbox Voice & Realtime 6.2 SoTA open-source TTS 25.4k★2/90d2 devs/90d -
Voice Mode (MCP) Voice & Realtime 6.0 Natural voice conversations with Claude Code 1.3k★412/90d4 devs/90d -
Bolna Voice & Realtime 5.9 Conversational voice AI agents 685★172/90d8 devs/90d -
Moshi Voice & Realtime 5.5 Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. 10.5k★3/90d2 devs/90d -
Higgs Audio Voice & Realtime 5.4 Text-audio foundation model from Boson AI 8.3k★1/90d1 devs/90d -
Speaches Voice & Realtime 5.4 Self-hosted OpenAI-API-compatible speech server bundling faster-whisper STT and Kokoro/Piper TTS with a realtime WebSocket endpoint. 3.4k★12/90d1 devs/90d -
faster-whisper Voice & Realtime 5.2 Faster Whisper transcription with CTranslate2 24k★0/90d0 devs/90d -
OpenVoiceOS Voice & Realtime 5.0 OpenVoiceOS Core, the FOSS Artificial Intelligence platform. 278★38/90d1 devs/90d -
Unmute Voice & Realtime 4.9 Make text LLMs listen and speak 1.3k★2/90d2 devs/90d -
Coqui TTS Voice & Realtime 4.8 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production 45.7k★0/90d0 devs/90d -
Bark Voice & Realtime 4.7 🔊 Text-Prompted Generative Audio Model 39.2k★0/90d0 devs/90d -
Kokoro Voice & Realtime 4.7 https://hf.co/hexgrad/Kokoro-82M 7.8k★0/90d0 devs/90d -
OpenVoice Voice & Realtime 4.6 Instant voice cloning by MIT and MyShell. Audio foundation model. 36.9k★0/90d0 devs/90d -
Dia Voice & Realtime 4.5 A TTS model capable of generating ultra-realistic dialogue in one pass. 19.3k★0/90d0 devs/90d -
Piper Voice & Realtime 4.5 A fast, local neural text to speech system 11.2k★0/90d0 devs/90d -
FastRTC Voice & Realtime 4.4 The python library for real-time communication 4.6k★0/90d0 devs/90d -
TEN VAD Voice & Realtime 4.4 Voice Activity Detector (VAD) : low-latency, high-performance and lightweight 2.2k★0/90d0 devs/90d -
Smart Turn Voice & Realtime 4.3 Open-source semantic turn-detection model supporting 23 languages with real-time CPU inference and no GPU required. 1.4k★0/90d0 devs/90d -
Sesame CSM Voice & Realtime 4.2 A Conversational Speech Generation Model 14.7k★0/90d0 devs/90d -
Orpheus TTS Voice & Realtime 4.1 Towards Human-Sounding Speech 6.2k★0/90d0 devs/90d -
Ultravox Voice & Realtime 4.1 A fast multimodal LLM for real-time voice 4.5k★0/90d0 devs/90d -
openWakeWord Voice & Realtime 4.0 An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity. 2.5k★0/90d0 devs/90d -
RealtimeVoiceChat Voice & Realtime 3.9 Have a natural, spoken conversation with AI! 3.8k★0/90d0 devs/90d -
Vocode Voice & Realtime 3.8 🤖 Build voice-based LLM agents. Modular + open source. 3.8k★0/90d0 devs/90d