Alternatives
Self-hosted alternatives to ElevenLabs
Projects in the registry that can run on your own hardware and serve at least one of the same use cases as ElevenLabs.
- Source
- Registry relations over fetched repository records — the evidence sits on each repository page
- Verified
- Evidence not verified
- Confidence
- High
01How this list was built
- Compared against
- ElevenLabs
- Delivery
- SaaS products
- Shared use cases
- Voice agent, AI video workflow, Translation
- Selection rule
- open source, or self-hostable, and shares a use case
- Candidates found
- 8
02Alternatives
ComfyUI
Self-hosted projects
Node-based interface for image and video generation models, where a pipeline is an explicit graph that can be saved, versioned and re-run. Runs locally on your own GPU.
- Repository
- comfyanonymous/ComfyUI
- Stars
- 133,870
- Licence
- GPL-3.0
- In stacks
- 0
Shares: Ai video workflow
faster-whisper
Libraries
Reimplementation of Whisper on CTranslate2 with substantially lower memory use and faster inference, including int8 execution on CPU. The usual engine behind self-hosted transcription.
- Repository
- SYSTRAN/faster-whisper
- Stars
- 25,259
- Licence
- MIT
- In stacks
- 2
Shares: Voice agent
LiveKit Agents
Hybrid — hosted or self-hosted
Framework for real-time voice and video agents on LiveKit’s WebRTC infrastructure, with turn detection, interruption handling and pluggable speech and model providers.
- Repository
- livekit/agents
- Stars
- 14,030
- Licence
- Apache-2.0
- In stacks
- 1
Shares: Voice agent
LMDeploy
Model servers
Serving toolkit from the InternLM team with its own inference engine and quantisation tooling, and strong coverage of Chinese open-weight model families.
- Repository
- InternLM/lmdeploy
- Stars
- 8,082
- Licence
- Apache-2.0
- In stacks
- 0
Shares: Translation
Open WebUI
Self-hosted projects
Self-hosted chat interface for local and hosted models, with user accounts, groups, document upload and built-in retrieval. Runs in Docker against Ollama, vLLM or any OpenAI-compatible endpoint.
- Repository
- open-webui/open-webui
- Stars
- 149,870
- Licence
- Other
- In stacks
- 5
Shares: Translation
PaddleOCR
Libraries
OCR toolkit with detection, recognition and layout models, including Chinese and other East Asian scripts, plus table and formula recognition. Runs offline on CPU or GPU.
- Repository
- PaddlePaddle/PaddleOCR
- Stars
- 88,941
- Licence
- Apache-2.0
- In stacks
- 0
Shares: Translation
Pipecat
Frameworks
Open-source framework for real-time voice and multimodal agents, composing speech-to-text, model and speech synthesis services into a streaming pipeline with barge-in support.
- Repository
- pipecat-ai/pipecat
- Stars
- 15,659
- Licence
- BSD-2-Clause
- In stacks
- 1
Shares: Voice agent
WhisperX
Libraries
Whisper-based transcription pipeline adding word-level timestamps, forced alignment and speaker diarisation. Runs locally on GPU for batch transcription of recordings.
- Repository
- m-bain/whisperX
- Stars
- 24,121
- Licence
- BSD-2-Clause
- In stacks
- 1
Shares: Translation
03Repository facts
| Repository | Stars | Health |
|---|---|---|
| comfyanonymous/ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. | 134k | Maintenance 80%, Releases 60%, Contributors 50%, Issues 63%, Community 100%75 |
| SYSTRAN/faster-whisperFaster Whisper transcription with CTranslate2 | 25k | Maintenance 20%, Releases 20%, Contributors 50%, Issues 87%, Community 88%48 |
| livekit/agentsA framework for building realtime voice AI agents | 14k | Maintenance 60%, Releases 60%, Contributors 50%, Issues 44%, Community 83%63 |
| InternLM/lmdeployLMDeploy is a toolkit for compressing, deploying, and serving LLMs. | 8.1k | Maintenance 80%, Releases 60%, Contributors 50%, Issues 26%, Community 78%66 |
| open-webui/open-webuiUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) | 150k | Maintenance 60%, Releases 60%, Contributors 50%, Issues 99%, Community 100%72 |
| PaddlePaddle/PaddleOCRTurn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. | 89k | Maintenance 60%, Releases 40%, Contributors 50%, Issues 97%, Community 99%68 |
| pipecat-ai/pipecatOpen Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community. | 16k | Maintenance 80%, Releases 80%, Contributors 50%, Issues 78%, Community 84%76 |
| m-bain/whisperXWhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization) | 24k | Maintenance 60%, Releases 40%, Contributors 50%, Issues 91%, Community 88%65 |
04Ask about your own case
Which alternative is right depends on how many people will use it, what the data is and what you can operate. Ask and the answer is researched for your organisation.