The Brainiall Pronunciation MCP server,
connected in one click.

“Use “assess_pronunciation”: Assess English pronunciation quality from audio. Scores pronunciation at four levels: overall, sentence, word, and phoneme. Each score is 0.”

“Use “check_pronunciation_service”: Check if the Brainiall Pronunciation service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error.”

“Use “get_phoneme_inventory”: Get the full phoneme inventory supported by the pronunciation scorer. Returns a list of all English phonemes the engine can assess, includi.”

“Use “transcribe_audio”: Transcribe audio to text with word-level timestamps. Converts spoken English audio into text with optional word-level timestamps and per-wo.”

assess_pronunciation — Assess English pronunciation quality from audio. Scores pronunciation at four levels: overall, sentence, word, and phoneme. Each score is 0

check_pronunciation_service — Check if the Brainiall Pronunciation service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error

get_phoneme_inventory — Get the full phoneme inventory supported by the pronunciation scorer. Returns a list of all English phonemes the engine can assess, includi

transcribe_audio — Transcribe audio to text with word-level timestamps. Converts spoken English audio into text with optional word-level timestamps and per-wo

check_stt_service — Check if the Brainiall Speech service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state

voice_id_enroll — Enroll a voiceprint for a speaker from ~2s of clear speech. Repeat with more clips to strengthen it. Only an irreversible embedding is stor

voice_id_verify — 1:1 verification — is this clip the enrolled speaker? Returns: dict with keys: similarity (float), match (bool), threshold (float).

voice_id_identify — 1:N identification — rank everyone enrolled in the group against this clip. Returns: dict with keys: candidates (list of {speaker_id, s