⚙

Settings

Configure backend URLs, API keys, voice folders, and playback preferences.

Settings

Configure the service URLs you actually use first. Advanced payloads, folders, and keys are tucked away below.

Local stack
Quick setup 1. Check core TTS URLs. 2. Point STT at Whisper, Parakeet, or the NVIDIA router. 3. Save settings.

Core connections

These are the endpoints you change most often. Qwen3 TTS, NVIDIA TTS, and STT are grouped separately.

TTS Text to Speech Qwen3 engines: clone, design, custom, streaming · Kokoro FastAPI
Uploaded/cloned WAV voices. Expected: POST /v1/audio/speech.
Prompt-designed voices and vd_... virtual voices.
Style over configured speakers such as Ryan, Vivian, Serena.
Progressive low-latency WAV playback.
OpenAI-compatible TTS. Built-in voices: af_bella, bf_emma, am_adam… ~300 MB RAM · ~0.1× CPU RTF.
NVIDIA speech stack router, Magpie TTS, Parakeet ASR, clone NIM
OpenAI-compatible base URL for the NVIDIA speech router.
Direct Magpie endpoint. Fixed speakers, not WAV cloning.
Direct Parakeet endpoint for transcription.
Magpie Zeroshot clone endpoint with audio_prompt.
Magpie Flow clone endpoint with audio_prompt and transcript.
STT Speech to Text Whisper, faster-whisper, whisper.cpp, Groq, Parakeet, NVIDIA router
Default recognition endpoint. Expected: POST /v1/audio/transcriptions.
GPU-accelerated Whisper via CTranslate2. ~70× RT · 1.5 GB VRAM · POST /v1/audio/transcriptions.
Lightweight C++ Whisper server. ~8–15× RT CPU · ~1 GB RAM · POST /v1/audio/transcriptions.
Used for Groq Whisper STT (whisper-large-v3-turbo) and Groq LLM. Free: 2 000 req/day. Fastest cloud transcription.

Playback behavior

Small behavior switches for previews and OpenAI-compatible TTS calls.

Buffered keeps Save WAV available. Streaming starts sooner.
Controls payload shape for the normal TTS API URL.
Advanced request payloads JSON extras sent to each backend
Extra fields for the 8020 WAV voice clone/base model.
Extra fields for the 8023 streaming model.
Extra fields for the CustomVoice backend.
Extra fields for Voice Design and virtual vd_... voices.
Usually empty. Magpie accepts fixed speaker voices such as sofia, aria, jason, leo, and john.
Optional multipart fields. The app supplies text, language, and audio_prompt.
Optional multipart fields. The app also sends the saved reference transcript.
Extra JSON fields for the Kokoro backend. Usually empty — voice is selected from the voice dropdown.
Voice folders container paths and Portainer volume mounts
Contains active_voices, hidden_voices, sounds, and metadata.
New cloned/exported voices are saved here.
API keys usually empty for local containers