# Open-source alternatives to Descript

> Open-source alternatives to Descript that run locally, allow commercial use and need no paid API include GPT-SoVITS (voice cloning and speech generation; MIT; runs on CPU) and Dia (voice cloning and speech generation; Apache-2.0; GPU, ~4.4GB+). None of the 9 projects we track covers all 3 Descript jobs, so most people combine two or more.

Descript: 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 (checked 2026-10-15). Facts checked 2026-10-16.

## Projects

| Project | Jobs | Runs locally | Commercial use | Paid services | Hardware |
|---|---|---|---|---|---|
| [GPT-SoVITS](https://repoquarry.dev/projects/gpt-sovits) | speech-generation, voice-cloning | Yes, local WebUI on GPU, Apple silicon or CPU; Docker images available | Yes, MIT code and core weights; check licences of optional third-party models you add (UVR5, Damo ASR, Faster Whisper) | None required | No minimum RAM/VRAM stated. Stated speed (v2 ProPlus): RTF 0.028 on RTX 4060 Ti, 0.014 on RTX 4090, 0.526 on an M4 CPU. Tested on CUDA, Apple silicon and CPU. |
| [Fish Speech](https://repoquarry.dev/projects/fish-speech) | speech-generation, voice-cloning | Yes, CLI, API server and WebUI, or Docker; Drama 3 needs an NVIDIA GPU, S2-Pro also runs on CPU | Only with Drama 3 and only while you and your affiliates earn under USD 500k a year; S2-Pro needs a paid licence for any commercial use; offering a hosted TTS/cloning service always needs a separate licence | None for local research/non-commercial use; a paid commercial licence is needed above the revenue cap or for hosted services | Drama 3 needs at least 48 GB GPU memory (FP8), NVIDIA only; S2-Pro needs at least 24 GB, NVIDIA GPU or CPU |
| [F5-TTS](https://repoquarry.dev/projects/f5-tts) | speech-generation, voice-cloning | Yes, local PyTorch on NVIDIA, AMD, Intel GPU or Apple Silicon; Docker image available | No with the released weights (CC-BY-NC-4.0); the MIT code could be used with your own commercially licensed weights | None required | Not documented; only a benchmark on a single NVIDIA L20 GPU is given |
| [Chatterbox](https://repoquarry.dev/projects/chatterbox) | speech-generation, voice-cloning | Yes, on GPU (CUDA), Apple MPS or CPU | Yes, MIT code and weights (generated audio is watermarked) | None required; Resemble AI's paid hosted TTS service is offered as an optional extra | Nano runs on CPU at about 3x realtime on 8 cores; no VRAM or RAM minimums stated |
| [Rescript](https://repoquarry.dev/projects/rescript) | transcript-editing, speech-recognition, speaker-identification | Yes, desktop app or browser; media processed on-device | No, the code licence is non-commercial (older MIT releases stay MIT) | None required | Uses WebGPU when available, WASM fallback otherwise; RAM not documented |
| [Coqui TTS](https://repoquarry.dev/projects/coqui-tts) | speech-generation, voice-cloning | Yes, Python library and CLI on CPU or GPU, plus a CPU Docker image | Code is usable commercially under MPL-2.0, but XTTS-v2 (the main voice cloning model) is non-commercial only, including its outputs; other models carry their own licences | None required | No RAM or VRAM requirements documented; code falls back to CPU when CUDA is unavailable and a CPU Docker image exists |
| [Dia](https://repoquarry.dev/projects/dia) | speech-generation, voice-cloning | Yes, on an NVIDIA GPU (CPU support not yet available) | Yes by licence (Apache-2.0 code and weights), though the README says the model is intended for research and educational use and forbids identity misuse and deceptive content | None required | NVIDIA GPU; about 4.4 GB VRAM in bfloat16/float16, about 7.9 GB in float32 (benchmarked on RTX 4090) |
| [OpenVoice](https://repoquarry.dev/projects/openvoice) | voice-cloning, speech-generation | Yes, Python package with notebooks and a local Gradio demo | Yes, MIT code and weights; V2 also needs MeloTTS, which is MIT | None required | Not documented |
| [StyleTTS 2](https://repoquarry.dev/projects/styletts2) | speech-generation, voice-cloning | Yes, Python/PyTorch inference via the provided notebooks | Code is MIT, but the pretrained weights have no formal licence (only disclosure/permission terms) and inference relies on a GPL-licensed phonemizer; an MIT-only package using gruut exists at lower quality | None required | Inference requirements not documented. CPU inference is suggested as a fix for noise on older GPUs. Fine-tuning example took about 4 hours on four NVIDIA A100s. |

## Common questions

### Is there a free, open-source alternative to Descript?

Yes. GPT-SoVITS, Fish Speech, Chatterbox, F5-TTS and StyleTTS 2 are free to download and run on your own computer without paid API keys. Each covers only part of what Descript does, so check which job you need.

### Can I do voice cloning locally without a Descript subscription?

Yes, with Fish Speech (Custom licence), GPT-SoVITS (MIT) and Chatterbox (MIT). Check the hardware notes and licence conditions on each page before you start.

### Which Descript alternatives can I use commercially?

Confirmed: Chatterbox, Dia, GPT-SoVITS and OpenVoice. With conditions: Coqui TTS, Fish Speech and StyleTTS 2. Not for commercial use: F5-TTS and Rescript, usually because the model weights are non-commercial. This is not legal advice; read each licence.

### Does any open-source project replace all of Descript?

Not as of 2026-10-16. Transcript-based editing, voice cloning and speech generation are covered by different projects.

---
Source: RepoQuarry (https://repoquarry.dev/alternatives/descript). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.