Connection check
verified live · 20h ago
kurdish-tts-stt
Kurdish (Sorani & Kurmanji) text-to-speech & speech-to-text — 664 AI voices. API key required.
Tools
5
GitHub stars
—
Installs / wk
—
Licence
—
Transport
streamable-http
Last checked
20h ago
Tools & capabilities
5 toolsRead from the running server on 20h ago.
list_dialects
context*
List the supported Kurdish dialects and their scripts. Static capability descriptor — costs nothing. List the supported Kurdish dialects and their scripts. Static capability descriptor — costs nothing.
list_voices
context*dialectmodel_version
List available Kurdish text-to-speech voices. Returns speaker ids (e.g. sorani_1, kurmanji_236) to use with synthesize_speech. Free metadata call — no credits consumed. List available Kurdish text-to-speech voices. Returns speaker ids (e.g. sorani_1, kurmanji_236) to use with synthesize_speech. Free metadata call — no credits consumed.
start_streaming_transcription
context*dialect*
Start a live streaming speech-to-text session. WARNING: calling this immediately consumes one streaming session from your STT plan quota — only call it when you are ready to connec… Start a live streaming speech-to-text session. WARNING: calling this immediately consumes one streaming session from your STT plan quota — only call it when you are ready to connect. Returns a websocket_url: open it, stream PCM16 mono 16kHz audio chunks, send {"type": "finalize"} to flush and {"type": "done"} to close. Session duration is limited by plan.
synthesize_speech
text*speedcontext*speaker_id*model_versioninclude_timestamps
Convert Kurdish text (Sorani or Kurmanji) to speech audio. Requires a TTS API key; characters are billed against your plan. Max 600 characters per call over MCP — for longer texts… Convert Kurdish text (Sorani or Kurmanji) to speech audio. Requires a TTS API key; characters are billed against your plan. Max 600 characters per call over MCP — for longer texts call POST https://www.kurdishtts.com/api/tts-proxy directly (binary WAV, higher plan limits). Note: speed is caller-facing (higher = faster).
transcribe_audio
context*dialect*filenamemime_typeaudio_base64*