Pricing

from $20.00 / 1,000 tool calls

Brainiall Speech MCP Server

Production speech AI tools for AI agents: Brainiall Pronunciation (0-100 phoneme/word/sentence scoring), Brainiall Speech (transcription with timestamps), Brainiall Speech Pro (99 languages + diarization), Brainiall Voice (12 voices). Sub-second p50.

Pricing

from $20.00 / 1,000 tool calls

Rating

0.0

(0)

Developer

Fabio Suizu

Actor stats

Bookmarked

Total users

Monthly active users

20 days ago

Last modified

Tools

Tool	Description
assess_pronunciation	Brainiall Pronunciation: score English pronunciation from audio (0-100 at overall, sentence, word, phoneme levels)
transcribe_audio	Brainiall Speech: convert spoken English to text with word-level timestamps
synthesize_speech	Brainiall Voice: generate natural speech from text (12 voices, American & British)
transcribe_audio_pro	Brainiall Speech Pro: 99 languages, speaker diarization
list_tts_voices	List available Brainiall Voice voices
check_pronunciation_service	Health check for the pronunciation engine
check_stt_service	Health check for the transcription engine
check_tts_service	Health check for the voice engine
check_whisper_service	Health check for the Speech Pro engine

Pronunciation Scoring

Returns scores (0-100) at four granularity levels:

Level	Description
Overall	Global pronunciation quality
Sentence	Sentence-level fluency and accuracy
Word	Per-word pronunciation scores
Phoneme	Individual sound accuracy (IPA + ARPAbet)

Performance

Accuracy: Exceeds human inter-annotator agreement (PCC 0.590 vs 0.555)
Validated: 9,259 utterances across 7 L1 backgrounds, zero errors
Latency: Sub-second p50 for pronunciation and transcription

How to Use

Connect to this Actor in MCP server (standby) mode and call the tools above. All tools accept and return base64-encoded audio.

Example: Pronunciation Assessment

{
  "audio_base64": "<base64-encoded-audio>",
  "text": "The quick brown fox jumps over the lazy dog"
}

Example: Text-to-Speech

{
  "text": "Hello, how are you today?",
  "voice": "af_heart",
  "speed": 1.0
}

Pricing

$0.02 per tool call (pay-per-event).

Technical Details

Engines: Brainiall Pronunciation, Brainiall Speech, Brainiall Speech Pro, Brainiall Voice
Audio: Supports WAV, MP3, OGG, FLAC, WebM
Backend: Brainiall production API (https://api.brainiall.com), auto-scaling

More from Brainiall

This MCP server covers the speech tools. The full Brainiall platform offers 19 specialty AI APIs + 5 bundles (NLP, vision, documents, fraud, authenticity and more) under one key.

Platform: https://app.brainiall.com
Docs: https://app.brainiall.com/en/docs
Demo: https://huggingface.co/spaces/fabiosuizu/pronunciation-assessment
Company: https://www.brainiall.com

Speech AI MCP Server

vivid_astronaut/pronunciation-assessment-mcp

Speech AI MCP server with 9 tools: pronunciation scoring (0-100 at phoneme/word/sentence level), speech-to-text with timestamps, text-to-speech with 12 English voices, and multilingual Whisper transcription (99 languages + speaker diarization). Sub-300ms latency. Pay-per-use: $0.02/call.

Fabio Suizu

Hugging Face Audio AI

alizarin_refrigerator-owner/hugging-face-audio-ai

Audio w/Hugging Face models speech recognition, text-to-speech & audio analysis Speech-to-Text: Transcribe audio Text-to-Speech: Generate natural speech Audio Classification: Classify sounds Voice Activity Detection: Detect speech Speaker Diarization: Identify speakers Music Generation: Create music

The Howlers

Text To Speech

vivid_astronaut/text-to-speech

Convert text to natural speech using AI voices. Multiple voices and languages available. Generate audio files for podcasts, videos, accessibility, and voice assistants.

Fabio Suizu

Speech To Text

vivid_astronaut/speech-to-text

Convert speech to text with high accuracy using Azure AI. Supports 100+ languages, speaker detection, and timestamps. Perfect for transcription, subtitles, and voice-to-text applications.

Fabio Suizu

YouTube Speech Dataset Builder

eternallabs/multilingual-codeswitching-scraper

Generate multilingual speech datasets from YouTube using WhisperX, transcription, language detection, and code-switch analysis for ASR training, benchmarking, and speech AI research.

Jona

Text to speech generator

akash9078/advanced-text-to-speech

Professional-grade Text-to-Speech (TTS) actor powered by advanced AI models. Convert any text into natural, human-like speech with 50+ premium voices across 9 languages. Perfect for content creation, accessibility, voiceovers, audiobooks, podcasts, and multilingual applications.

Akash Kumar Naik

Text to Speech Generator

moving_beacon-owner1/my-actor-30

Convert text into natural-sounding speech in multiple languages with ease.

Jamshaid Arif

Speech Lang Pathologist Email Scraper

contacts-api/speech-lang-pathologist-email-scraper

Speech-language pathologist email scraper to extract verified speech therapist emails from clinics, hospitals, rehabilitation centers, schools, and healthcare directories 📧🗣️ Perfect for healthcare outreach, recruitment, and speech therapy lead generation.

Lead Heaven

Google Free Text to Speech

jupri/google-speech

Use free Google Text to Speech to translate text into voice

cat

300

Text To Speech

calm_necessity/text-to-speech

AI Text-to-Speech API that converts written text into high-quality natural voice audio. Supports multiple voices, languages, adjustable speed and pitch, ideal for audiobooks, podcasts, accessibility, automation, and voice-enabled applications.