Brainiall Pronunciation
Server Details
Pronunciation assessment, phoneme scoring, speaker voice ID, audio transcription, speech synthesis.
- Status
- Healthy
- Uptime
- 27.3% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
Most tools map to clearly distinct actions, but transcribe_audio and transcribe_audio_pro are near-duplicates and the four check_*_service tools require careful reading. The detailed descriptions make the distinctions recoverable, so confusion should be rare.
The set overwhelmingly follows a snake_case verb_* pattern, and the voice_id_* family is internally consistent. Minor deviations like get_phoneme_inventory vs list_tts_voices and the _pro suffix on transcribe_audio_pro keep it from being perfect.
Fourteen tools is within a reasonable range, but the server bundles pronunciation, STT, TTS, voice ID, and four health checks, making it feel broader than the 'Pronunciation' name suggests. A few health checks could be consolidated, but nothing is excessive.
Core pronunciation, transcription, and synthesis workflows are present, but the voice ID portion has create/list/verify/identify with no way to delete or unenroll a speaker. That is a notable lifecycle gap in an otherwise fairly complete speech toolkit.
Available Tools
14 toolsassess_pronunciationAssess PronunciationARead-onlyIdempotentInspect
Assess English pronunciation quality from audio.
Scores pronunciation at four levels: overall, sentence, word, and phoneme. Each score is 0-100. Phonemes are returned in both IPA and ARPAbet notation. Sub-300ms inference latency.
Args: audio_base64: Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats. text: The reference English text that the speaker was expected to read aloud. audio_format: Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'. Defaults to 'wav'.
Returns: dict with keys: - overallScore (int 0-100): Overall pronunciation quality - sentenceScore (int 0-100): Sentence-level fluency and accuracy - words (list): Per-word scores, each containing: - word (str): The word - score (int 0-100): Word pronunciation score - phonemes (list): Per-phoneme scores with IPA/ARPAbet notation - decodedTranscript (str): What the model heard (ASR transcript) - transcript (str): Reference text - confidence (float 0-1): Scoring confidence - warnings (list[str]): Quality warnings if any - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Inputs: text (required), audio_base64 (required), audio_format.
check_pronunciation_serviceCheck Pronunciation ServiceARead-onlyIdempotentInspect
Check if the Brainiall Pronunciation service is healthy and ready.
Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the scoring model is loaded - version (str): API version
Inputs: no named parameters.
check_stt_serviceCheck STT ServiceARead-onlyIdempotentInspect
Check if the Brainiall Speech service is healthy and ready.
Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the speech-recognition model is loaded - version (str): API version
Inputs: no named parameters.
check_tts_serviceCheck TTS ServiceARead-onlyIdempotentInspect
Check if the Brainiall Voice service is healthy and ready.
Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the synthesis model is loaded - version (str): API version
Inputs: no named parameters.
check_whisper_serviceCheck Brainiall Speech Pro ServiceBRead-onlyIdempotentInspect
Check if the Brainiall Speech Pro service is healthy and ready.
Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the Brainiall Speech Pro engine is loaded - diarizeLoaded (bool): Whether the diarization pipeline is loaded - version (str): API version - modelName (str): Engine version identifier
Inputs: no named parameters.
get_phoneme_inventoryGet Phoneme InventoryARead-onlyIdempotentInspect
Get the full phoneme inventory supported by the pronunciation scorer.
Returns a list of all English phonemes the engine can assess, including ARPAbet symbol, IPA equivalent, example word, and phoneme category (vowel, consonant, diphthong).
Returns: list of dicts, each with keys: - arpabet (str): ARPAbet symbol (e.g. 'AA', 'TH') - ipa (str): IPA notation - example (str): Example word containing the phoneme - category (str): vowel, consonant, or diphthong
Inputs: no named parameters.
list_tts_voicesList TTS VoicesARead-onlyIdempotentInspect
List all available Brainiall Voice synthesis voices with metadata.
Returns: dict with keys: - voices (list): Available voices, each with id, name, gender, accent, grade - defaultVoice (str): Default voice ID
Inputs: no named parameters.
synthesize_speechSynthesize SpeechARead-onlyIdempotentInspect
Generate natural speech audio from English text.
Produces high-quality speech with 12 English voices. Returns base64-encoded WAV audio (16-bit PCM, 24kHz mono) along with metadata.
Available voices:
af_heart (default), af_bella, af_nicole, af_sarah, af_sky (American female)
am_adam, am_michael (American male)
bf_emma, bf_isabella (British female)
bm_george, bm_lewis, bm_daniel (British male)
Args: text: English text to synthesize (1-5000 characters). voice: Voice ID. See list above. Defaults to 'af_heart'. speed: Speed multiplier from 0.5 to 2.0 (default: 1.0).
Returns: dict with keys: - audio_base64 (str): Base64-encoded WAV audio (16-bit PCM, 24kHz) - duration_ms (str): Audio duration in milliseconds - voice (str): Voice ID used - text_length (str): Input text character count - processing_ms (str): Synthesis time in milliseconds
Inputs: text (required), speed, voice.
transcribe_audioTranscribe AudioARead-onlyIdempotentInspect
Transcribe audio to text with word-level timestamps.
Converts spoken English audio into text with optional word-level timestamps and per-word confidence scores.
Args: audio_base64: Base64-encoded audio data (WAV, MP3, OGG, FLAC, WebM). audio_format: Audio format hint. Auto-detected from magic bytes if omitted. include_timestamps: Whether to include word-level timing (default: true).
Returns: dict with keys: - text (str): Full decoded transcript - words (list): Per-word results with timestamps, each containing: - word (str): The transcribed word - start (float): Start time in seconds - end (float): End time in seconds - confidence (float 0-1): Word-level confidence - audioDurationMs (int): Audio duration in milliseconds - metadata (dict): Processing time, audio length, model version - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Inputs: audio_base64 (required), audio_format, include_timestamps.
transcribe_audio_proTranscribe Audio ProARead-onlyIdempotentInspect
Transcribe audio with Brainiall Speech Pro — multilingual transcription.
Supports 99 languages with automatic language detection, word-level timestamps, per-word confidence scores, and optional speaker diarization (identifies who spoke each word). Best-in-class WER (~2%).
Args: audio_base64: Base64-encoded audio (WAV, MP3, OGG, FLAC, WebM). language: Language code. Auto-detected if omitted. Supports 99 languages. diarize: Enable speaker diarization (default: false). When true, each word includes a speaker label (e.g. SPEAKER_00, SPEAKER_01).
Returns: dict with keys: - text (str): Full decoded transcript - words (list): Per-word results with timestamps, each containing: - word (str), start (float), end (float), confidence (float 0-1) - speaker (str|null): Speaker label when diarize=true - speakers (dict|null): Speaker info with count and labels - audioDurationMs (int): Audio duration in milliseconds - metadata (dict): Processing time, language, languageProbability - audioQuality (dict): Audio metrics (SNR, peak/RMS dB, etc.)
Inputs: audio_base64 (required), diarize, language.
voice_id_enrollEnroll VoiceprintAInspect
Enroll a voiceprint for a speaker from ~2s of clear speech. Repeat with more clips to strengthen it.
Only an irreversible embedding is stored — never the raw audio.
Returns: dict with keys: speaker_id (str), n_samples (int), enrolled (bool).
Inputs: audio (required), group_id (required), speaker_id (required).
voice_id_identifyIdentify Speaker (1:N)ARead-onlyIdempotentInspect
1:N identification — rank everyone enrolled in the group against this clip.
Returns: dict with keys: candidates (list of {speaker_id, similarity}, best first).
Inputs: audio (required), group_id (required), top_k.
voice_id_list_speakersList Enrolled SpeakersARead-onlyIdempotentInspect
List the speakers enrolled in a group.
Returns: dict with keys: speakers (list of {speaker_id, n_samples, ...}).
Inputs: group_id (required).
voice_id_verifyVerify Speaker (1:1)ARead-onlyIdempotentInspect
1:1 verification — is this clip the enrolled speaker?
Returns: dict with keys: similarity (float), match (bool), threshold (float).
Inputs: audio (required), group_id (required), speaker_id (required), threshold.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Pronunciation scoring, speech-to-text, and text-to-speech for language learning
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.
Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.
Related MCP Servers
- AlicenseAqualityDmaintenanceAI-powered speech tools by Brainiall: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection, and text-to-speech with multiple voices.41MIT
- FlicenseNot gradedqualityDmaintenanceGives your AI agent real-time pronunciation scoring and multi-dimensional speech assessment through CHIVOX server.-
- AlicenseAqualityCmaintenanceEnables MCP clients to fetch supported languages and limitations, assess pronunciation from audio against reference text in ten languages, and explain returned assessment results locally.3MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to transcribe audio into timestamped transcripts and subtitles, synthesize speech from text, and clone voices from authorized reference recordings, with durable asynchronous jobs and optional on-demand GPU workers.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.