Connect cloud or local services for speech recognition, synthesis, and text generation.
Used for auto-transcribing reference audio. The app calls these when you click Re-recognise text.
https://api.groq.com/openai/v1
https://api-inference.huggingface.co/models/openai/whisper-large-v3
https://api.assemblyai.com/v2/transcript
Cloud TTS backends you can add as routing targets alongside your local cloned voices.
https://api.elevenlabs.io/v1/text-to-speech
https://api.fish.audio/v1/tts
Use LLMs to generate text for TTS, write scripts, clean transcripts, or power agentic voice pipelines.
https://api.groq.com/openai/v1
https://openrouter.ai/api/v1
https://generativelanguage.googleapis.com/v1beta/openai/
gemini-2.5-flashhttps://api.mistral.ai/v1
Run everything on your own hardware — no API key, no rate limits, no data leaves your machine.
Easiest local LLM setup. Pull any model with one command. Runs Llama, Mistral, Qwen, Phi, Gemma and many more.
http://localhost:11434/v1
curl https://ollama.ai/install.sh | sh ollama pull llama3.3
High-throughput GPU inference. Already in your Docker stack. Serve any HuggingFace model with PagedAttention.
http://localhost:8000/v1
--model Qwen/Qwen3-8B \ --served-model-name qwen3-8b
GUI app for running quantized models. Built-in model browser, chat UI, and a local server with OpenAI API.
http://localhost:1234/v1
Developer tab → Start server → Port 1234 Check "Enable CORS" for browser access
Lightweight GGUF model server. Minimal RAM usage. Runs on CPU or GPU. Great for embedding in Docker.
http://localhost:8080/v1
docker run -p 8080:8080 ghcr.io/ggml-org/llama.cpp:server \ -hf QuantFactory/Meta-Llama-3-8B-GGUF \ -hff Meta-Llama-3-8B.Q4_K_M.gguf
Drop-in local replacement for the Whisper API. GPU-accelerated via CTranslate2. OpenAI-compatible endpoint.
http://localhost:8000/v1
services:
whisper:
image: fedirz/faster-whisper-server:latest-cuda
ports: ["8000:8000"]
environment:
- WHISPER__MODEL=large-v3
deploy:
resources:
reservations:
devices: [{driver: nvidia, count: 1, capabilities: [gpu]}]
Minimal C++ Whisper with a built-in HTTP server. CPU or Metal/CUDA. Low memory, fast on consumer hardware.
http://localhost:8080
git clone https://github.com/ggml-org/whisper.cpp cd whisper.cpp && cmake -B build && cmake --build build -j ./build/bin/whisper-server \ -m models/ggml-large-v3.bin --port 8080
Lightning-fast offline TTS. Runs on CPU in real time. 50+ language voices available. Ideal for low-latency pipelines.
localhost:10200
docker run -p 10200:10200 \ rhasspy/wyoming-piper \ --voice en_US-lessac-medium
Kokoro-82M running behind an OpenAI-compatible TTS endpoint. Drop-in replacement for OpenAI’s TTS API.
http://localhost:8880/v1/audio/speech
docker run -p 8880:8880 \ ghcr.io/remsky/kokoro-fastapi-cpu:v0.2.2 # GPU: docker run -p 8880:8880 --gpus all \ ghcr.io/remsky/kokoro-fastapi-gpu:v0.2.2
Coqui XTTS — multilingual voice cloning from a 6-second sample. 17 languages. Compatible with this app’s voice library.
http://localhost:8020/tts_to_audio
docker run -p 8020:80 --gpus all \ -v /voices:/voices \ daswer123/xtts-api-server:latest
All OpenAI-compatible services work the same way: open App Routing in the sidebar, add a new backend entry with the local URL as base endpoint, and leave the API key field empty (or enter any string — it’s ignored by local servers). Set it as the default backend for the voice type you want (clone, design, or tryout) and the app will start routing requests to it immediately.