New in Speech and audio
17 new repos on our list for this job.
Newest first. Growth cannot be measured yet, so they are listed separately. How we rank
New to our list
| Rank | Name |
|---|---|
| 1. | AfriSpeech /africa-tts Text-to-speech for 92 African languages + English (Pocket TTS, IPA via africa-g2p): inference, training recipe, sherpa-onnx mobile deployment 18 starsThis week: Not stated |
| 2. | alexturkey /voxcpm2-turkce-ses-tasarimi Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read text in 30 languages. Patched audio.cpp, local UI in 30 languages, 14 ready-made voices. 399 stars+19 this week |
| 3. | aligh98 /tts-director Agent skill that directs scripts for TTS (ElevenLabs v3/v4 tags): rewrite for the ear, tag budget, free linter, A/B tester. | اسکیلی برای کارگردانی متن قبل از TTS: بازنویسی برای گوش، تگگذاری بدون زیادهروی، لینتر رایگان و تست A/B. فارسیمحور. 81 stars+22 this week |
| 4. | C4rohan /Lampline Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX. 491 stars+29 this week |
| 5. | christos-antono /NPCTalk Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example. 228 stars+13 this week |
| 6. | FlaxXTT /Typeleast TypeLeast：按一下快捷键说话，本机识别（SenseVoice），用你自己的大模型 API Key 整理成通顺文字，直接写进光标处。macOS + Windows 11。 121 stars+36 this week |
| 7. | hehehai /AudioSmith Speech, voices, stories, audiobooks, dubbing and transcription, made on your Mac. Free and open source. 227 stars+32 this week |
| 8. | izwi-ai /izwi Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API. 450 starsThis week: Not stated |
| 9. | joeynyc /spark-voice Voice assistant, voice studio and AI podcast that run entirely on NVIDIA DGX Spark. Pluggable models. 10 stars+1 this week |
| 10. | KorenKrita /simul-subtitle 日语、英语视频与直播实时同传悬浮字幕（Android / macOS / Windows）｜本地离线语音识别 · 自备 LLM 翻译（BYOK） 105 stars+10 this week |
| 11. | ozguradmin /ahenk-turkish-tts Ahenk: açık Türkçe metinden sese. Open Turkish text-to-speech: VoxCPM2 LoRA (Ahenk), 8.6M on-device model (Ahenk Cep), trnorm text normaliser, TR-Zor benchmark 109 stars+4 this week |
| 12. | PedroMarinhoDev /ComfyUI-Drama3 Fish Audio Drama 3 text to speech, natively in ComfyUI: voice cloning, dialogue and inline cues on cards from 8 GB, plus a native Qwen3-ASR. Built with Fish Audio. 166 stars+27 this week |
| 13. | raullenchai /esp32-thinks A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk. 262 stars+1 this week |
| 14. | tancheng33 /tingo 开过的会，都听过。本地 AI 会议纪要：会议录音转文字、区分说话人、自动生成纪要和待办，支持腾讯会议/飞书/Zoom，录音不上传 · Local-first AI meeting notes for Mac: on-device transcription, speaker diarization, minutes linked to quotes. Open-source Otter/Granola alternative 43 stars+35 this week |
| 15. | vatavale /folivox Turn any e-book into a chaptered audiobook in your own voice: free, fully local. CosyVoice 3 or Fish Audio Drama 3 (80+ languages, several voices), no cloud needed 112 stars+2 this week |
| 16. | VoxRT /LinnetTTS Lightweight on-device text-to-speech: flow LM over a continuous-latent codec, Rust runtime, Android/iOS/Linux/Python 25 stars+25 this week |
| 17. | zephyr4123 /speakmore SpeakMore：口述成文，划词即译。开源、免费的语音输入与翻译工具，支持 Mac 与 Windows：语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务，语音输入亦可完全在本机运行。附 Typeless 逆向分析。 194 stars+13 this week |