# Open-source alternatives for Voice AI

> Speech generation, voice cloning, transcription and voice agents.

## Paid products
- [Open-source alternatives to Descript](https://repoquarry.dev/alternatives/descript.md): Paid audio and video editor where you edit media by editing its transcript, with AI voices and voice clones. Pricing: Free plan (1 media hour/month); Hobbyist $24/month, or $16/month billed annually.
- [Open-source alternatives to ElevenLabs](https://repoquarry.dev/alternatives/elevenlabs.md): Paid voice AI platform for speech generation, voice cloning, transcription and voice agents. Pricing: Free tier (10k credits); paid plans from $6/month, or $5/month billed annually.
- [Open-source alternatives to Granola](https://repoquarry.dev/alternatives/granola.md): Paid AI notepad that transcribes your meetings without a bot joining and turns your notes into AI meeting notes. Pricing: Basic free (30 days of meeting history); Business $14 per user/month; Enterprise $35 per user/month.
- [Open-source alternatives to Otter.ai](https://repoquarry.dev/alternatives/otter-ai.md): Paid AI meeting assistant that transcribes meetings live, labels speakers and writes summaries. Pricing: Free Basic plan (300 min/month); Pro $16.99/month, or $8.33/month billed annually.
- [Open-source alternatives to Vapi](https://repoquarry.dev/alternatives/vapi.md): Paid developer platform for building voice agents that answer and make phone calls. Pricing: Pay as you go: $5 free credit, $0.05/min hosting plus provider costs; Core plan $29/month.

## Top ranked projects
1. [VoiceStudio](https://repoquarry.dev/projects/voicestudio.md): Local desktop app for voice cloning, voice design, video dubbing, dictation, transcription and audiobooks, built on OmniVoice and other engines. Commercial use: No.
2. [GPT-SoVITS](https://repoquarry.dev/projects/gpt-sovits.md): Few-shot voice cloning and TTS WebUI; 5-second zero-shot or 1-minute fine-tune, five languages, MIT code and weights. Commercial use: Confirmed.
3. [whisper.cpp](https://repoquarry.dev/projects/whisper-cpp.md): Dependency-free C/C++ port of OpenAI's Whisper speech recognition, running on CPU or GPU across desktop, mobile and the browser. Commercial use: Confirmed.
4. [Whisper](https://repoquarry.dev/projects/whisper.md): OpenAI's general-purpose speech recognition model for multilingual transcription, translation to English and language ID. Commercial use: Confirmed.
5. [Fish Speech](https://repoquarry.dev/projects/fish-speech.md): Fish Audio's multilingual TTS and voice cloning stack (Drama 3, S2-Pro) under a source-available community licence. Commercial use: Partial.
6. [faster-whisper](https://repoquarry.dev/projects/faster-whisper.md): Reimplementation of OpenAI Whisper on CTranslate2, up to 4x faster with less memory, with int8 on CPU or GPU. Commercial use: Confirmed.
7. [WhisperX](https://repoquarry.dev/projects/whisperx.md): Fast batched Whisper transcription with word-level timestamps via wav2vec2 alignment and pyannote speaker diarization. Commercial use: Partial.
8. [Meetily](https://repoquarry.dev/projects/meetily.md): Local AI meeting assistant that records mic and system audio, transcribes live with Whisper or Parakeet and summarises with an LLM. Commercial use: Confirmed.
9. [LiveKit Agents](https://repoquarry.dev/projects/livekit-agents.md): Python framework for real-time voice agents as server-side participants in LiveKit WebRTC rooms, with STT/LLM/TTS plugins. Commercial use: Partial.
10. [FluidVoice](https://repoquarry.dev/projects/fluidvoice.md): On-device voice dictation app for macOS that also records meetings (FluidMeet) with live captions, speaker labels and transcripts. Commercial use: Partial.
11. [Piper](https://repoquarry.dev/projects/piper.md): Fast, local neural text-to-speech engine with downloadable voices in 40+ languages, used by Home Assistant and NVDA. Commercial use: Partial.
12. [F5-TTS](https://repoquarry.dev/projects/f5-tts.md): Flow-matching text-to-speech research model that clones a voice zero-shot from a reference audio clip. Commercial use: No.
13. [Chatterbox](https://repoquarry.dev/projects/chatterbox.md): Resemble AI's family of open TTS models (Turbo, Nano, Multilingual) with zero-shot voice cloning from a reference clip. Commercial use: Confirmed.
14. [Pipecat](https://repoquarry.dev/projects/pipecat.md): Open-source Python framework for real-time voice and multimodal agents that plugs together STT, LLM, TTS and transports. Commercial use: Confirmed.
15. [Scriberr](https://repoquarry.dev/projects/scriberr.md): Self-hosted web app for offline transcription with Whisper, Parakeet or Canary, speaker diarization and LLM summaries. Commercial use: Confirmed.
---
Source: RepoQuarry (https://repoquarry.dev/categories/voice). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.