Audio
argmax-oss-swift
On-device Speech AI for Apple Silicon
★ 6,4k estrellasMIT
Ver la guía →// audio · k2-fsa/sherpa-onnx
sherpa-onnx
sherpa-onnx es un proyecto de audio de código abierto de k2-fsa (k2-fsa/sherpa-onnx en GitHub). Tiene 15.092 estrellas en GitHub y 1.745 bifurcaciones, se publica bajo la licencia Apache-2.0 y se actualizó por última vez en GitHub el 22 de septiembre de 2026.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet co…
★ 15,1k estrellas⑂ 1,7k bifurcacionesApache-2.0actualizado sep 2026
▦ visual: el README de este proyecto no incluye ninguna captura incrustable,
así que aquí va un marcador. La guía de abajo está completa de todos modos.
así que aquí va un marcador. La guía de abajo está completa de todos modos.
// datos del proyecto
Datos del proyecto
- Repositorio
- k2-fsa/sherpa-onnx
- Estrellas en GitHub
- 15.092
- Bifurcaciones
- 1.745
- Licencia
- Apache-2.0
- Última actualización en GitHub
- 22 de septiembre de 2026
- Categoría
- Audio
- Tipo de ficha
- Guía de instalación completa
- Sitio oficial
- Official site
// cómo funciona
Cómo funciona
- Pick the job
Transcription, synthesis, voice changing, or editing — each tool here majors in one.
- Install and set up
Binaries, pip packages, or Docker; models download on first run for AI tools.
- Feed it audio or text
Drop in a recording or type what you want spoken.
- Export the result
WAV/MP3/OGG outputs drop straight into editors or apps.
// características
Por qué gusta tanto
Multilingual
Dozens of languages supported, not just English.
Real-time options
Streaming transcription and TTS for live applications.
Diarization
Tell speakers apart in meetings and interviews automatically.
Voice cloning
Clone a voice from a short sample for narration and dubbing.
State-of-the-art models
Whisper-grade transcription and natural neural voices, free.
Offline capable
Many run fully on-device — nothing you say leaves the machine.
Advertisement
// ejecútalo
Ejecútalo tú mismo
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/k2-fsa/sherpa-onnx.git cd sherpa-onnx - Step 2 — Check the README
Every project documents its own setup; start with install requirements.
cat README.md | head -60 - Step 3 — Run it
Follow the project's launch command — Docker, pip, npm, or a binary release.
# see README for the exact launch command
// casos de uso
Qué puedes crear
- Transcribe meetings, lectures, and interviews.
- Generate voiceovers without a studio.
- Clone voices for dubbing and accessibility.
- Clean up and edit recordings.
Advertisement
// preguntas frecuentes
Preguntas frecuentes
Who maintains sherpa-onnx?
It is an open-source project at k2-fsa/sherpa-onnx with 1,745 forks. Check the repo's contributors and recent commits to see how active maintenance is.
Is sherpa-onnx free for commercial use?
Apache 2.0 licensed — commercial use allowed with attribution.
Can I use the voices commercially?
Check each license — many allow it, but voice-cloning has ethical and legal boundaries.
How accurate is the transcription?
Whisper-class models rival paid services on clear audio; noisy recordings need cleanup first.
Which languages are supported?
Dozens; English is strongest, major world languages are solid.
// sigue explorando
Herramientas similares
Audio
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
★ 62,3k estrellasMIT
Ver la guía →Audio
audacity
Audio Editor
★ 18,6k estrellasCustom
Ver la guía →Audio
sherpa
A speech-to-text server framework built on next-generation Kaldi.
★ 998 estrellasApache-2.0
Ver la guía →Audio
pyttsx3
Offline text-to-speech for Python — uses your operating system's own voices, no internet needed
★ 2,5k estrellasMPL-2.0
Ver la guía →Audio
FunASR
A complete open-source speech recognition toolkit - ASR, VAD, diarization and serving
★ 20,6k estrellasMIT
Ver la guía →// alternativas
Alternativas en Audio
Los demás proyectos de Audio con más estrellas del catálogo de LibreAI: la lista realista de alternativas si sherpa-onnx no es lo que buscas.
- MoneyPrinterTurbo★ 128,3k
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109,9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62,3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60,2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54,1k
Port of OpenAI's Whisper model in C/C++
// más en audio
Más en Audio
Proyectos de Audio cercanos en el catálogo, los más próximos en estrellas a sherpa-onnx: sigue explorando a ambos lados.
- F5 TTS★ 15,3k
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
- Qwen3-TTS★ 13,6k
Alibaba's open voice models: expressive, streaming-capable speech with free-form voice design.
- leon★ 17,6k
🧠 Leon is your open-source personal assistant.
- voice-pro★ 13,0k
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio proce…
- Speech★ 18,5k
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recogni…
- PaddleSpeech★ 12,7k
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text…
Consigue sherpa-onnx
Gratis y abierto: consigue el código fuente, dale una estrella al repositorio y empieza a crear.