RapidSpeech Server — Test Console

not connected

Capability coverage one console · local first

HTTP ASR / TTSOpenAI-compatible transcription and speech endpoints.
Streaming ASRMicrophone or file input, pure stream and VAD segmentation.
Streaming TTSTrue chunk streaming, sentence segmentation, latency and RTF.
Observer bridgeOptional ffmpeg source, video, RSS/CPU and soak-test alerts.

Model selection registry · download · hot load

Connect to load the model registry.

HTTP transcription POST /v1/audio/transcriptions

HTTP speech POST /v1/audio/speech

WS streaming ASR /asr/stream

Audio
0.0s
16 kHz mono
Level
-120 dB
peak -120 dB
Messages
0
0 finals
ASR idle
0s
since last event

WS VAD + ASR /asr/vad

WS TTS /tts/stream · /tts/segmented

First audio
-
request to first chunk
Chunks
0
0 segments
Audio
0.00s
received PCM
Wall / RTF
-
RTF -
Buffer ahead
-
positive is healthy

ASR Observer bridge optional observer.py on :8090

events disconnected
This bridge keeps ffmpeg, video preview, process RSS/CPU, idle and RSS-slope checks in the existing observer backend. Start it separately with python3 examples/server/asr-observer/observer.py.
Source audio
0.0s
0.00 MB
Level
-120 dB
peak -120 dB
rs-server
n/a
cpu n/a
ffmpeg
n/a
cpu n/a
Idle
0s
source 0s
RSS slope
n/a
ffmpeg n/a
No video frames
Observer transcript
No observer alerts

Log