io.github.fasuizu-br/speech-ai

Official10 tools

by fasuizu-br · Python

Speech AI - Pronunciation, STT & TTS

Pronunciation scoring, speech-to-text, and text-to-speech for language learning

Pronunciation scoring, speech-to-text, and text-to-speech for language learning.

Topics

ai-agentsapi-exampleslanguage-learningmcppronunciationspeech-aispeech-to-texttext-to-speech

Captured live from the server via tools/list.

assess_pronunciation

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.)

Parameters (3)

audio_base64stringrequired
Base64-encoded audio data. Supports WAV, MP3, OGG, and WebM formats.
textstringrequired
The reference English text that the speaker was expected to read aloud.
audio_formatstring
Audio format hint — one of 'wav', 'mp3', 'ogg', 'webm'.

check_pronunciation_service

Check if the pronunciation assessment 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

No parameters.

get_phoneme_inventory

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

No parameters.

transcribe_audio

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.)

Parameters (3)

audio_base64stringrequired
Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.
audio_formatany
Audio format hint — 'wav', 'mp3', 'ogg', 'flac', 'webm'. Auto-detected if omitted.
include_timestampsboolean
If true, include word-level start/end times and confidence.

check_stt_service

Check if the speech-to-text service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the STT model is loaded - version (str): API version

No parameters.

synthesize_speech

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

Parameters (3)

textstringrequired
English text to convert to speech. Max 5000 characters.
voiceany
Voice ID (e.g. 'af_heart', 'am_adam'). Uses default if omitted.
speednumber
Speech speed multiplier (0.5 = half speed, 2.0 = double).

list_tts_voices

List all available text-to-speech voices with metadata. Returns: dict with keys: - voices (list): Available voices, each with id, name, gender, accent, grade - defaultVoice (str): Default voice ID

No parameters.

check_tts_service

Check if the text-to-speech service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the TTS model is loaded - version (str): API version

No parameters.

transcribe_audio_pro

Transcribe audio with Whisper Large V3 Turbo — multilingual STT. 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.)

Parameters (3)

audio_base64stringrequired
Base64-encoded audio data. Supports WAV, MP3, OGG, FLAC, and WebM formats.
languageany
Language code (e.g. 'en', 'es', 'zh'). Auto-detected when omitted.
diarizeboolean
Enable speaker diarization to identify who spoke each word.

check_whisper_service

Check if the Whisper STT Pro service is healthy and ready. Returns: dict with keys: - status (str): 'healthy' or error state - modelLoaded (bool): Whether the Whisper model is loaded - diarizeLoaded (bool): Whether the diarization pipeline is loaded - version (str): API version - modelName (str): Whisper model name (e.g. 'large-v3-turbo')

No parameters.

README.md7 KBView on GitHub

Brainiall AI APIs

Production AI APIs for speech, text, image, and LLM inference. Available as REST endpoints and MCP servers for AI agents.

Base URL: https://apim-ai-apis.azure-api.net Full API reference for LLMs: llms-full.txt | llms.txt

Products

Product	Endpoints	Latency	Notes
Pronunciation Assessment	`/v1/pronunciation/assess/base64`	<500ms	17MB ONNX, per-phoneme scoring (39 ARPAbet)
Text-to-Speech	`/v1/tts/synthesize`	<1s	12 voices (American + British), 24kHz WAV
Speech-to-Text	`/v1/stt/transcribe/base64`	<500ms	Compact 17MB model, English, word timestamps
Whisper Pro	`/v1/whisper/transcribe/base64`	<3s	99 languages, speaker diarization
NLP Suite	`/v1/nlp/{toxicity,sentiment,entities,pii,language}`	<50ms	CPU-only, ONNX, 5 endpoints
Image Processing	`/v1/image/{remove-background,upscale,restore-face}/base64`	<3s	GPU (A10), BiRefNet + ESRGAN + GFPGAN
LLM Gateway	`/v1/chat/completions`	varies	113+ models, OpenAI-compatible, streaming

Authentication

Include ONE of these headers in every request:

code

Ocp-Apim-Subscription-Key: YOUR_KEY
Authorization: Bearer YOUR_KEY
api-key: YOUR_KEY

Get API keys at the portal (GitHub sign-in, purchase credits, create key).

Quick Start

Python — LLM Gateway (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    base_url="https://apim-ai-apis.azure-api.net/v1",
    api_key="YOUR_KEY"
)

response = client.chat.completions.create(
    model="claude-sonnet",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Python — Pronunciation Assessment

python

import requests, base64

audio_b64 = base64.b64encode(open("audio.wav", "rb").read()).decode()
r = requests.post(
    "https://apim-ai-apis.azure-api.net/v1/pronunciation/assess/base64",
    headers={"Ocp-Apim-Subscription-Key": "YOUR_KEY"},
    json={"audio": audio_b64, "text": "Hello world", "format": "wav"}
)
print(r.json()["overallScore"])  # 0-100

Python — NLP Pipeline

python

import requests

headers = {"Ocp-Apim-Subscription-Key": "YOUR_KEY"}
base = "https://apim-ai-apis.azure-api.net/v1/nlp"

# Sentiment
r = requests.post(f"{base}/sentiment", headers=headers, json={"text": "I love this!"})
print(r.json())  # {"label": "positive", "score": 0.9987}

# PII detection with redaction
r = requests.post(f"{base}/pii", headers=headers, json={"text": "Email john@acme.com", "redact": True})
print(r.json()["redacted_text"])  # "Email [EMAIL]"

Node.js — LLM Gateway

javascript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://apim-ai-apis.azure-api.net/v1",
  apiKey: "YOUR_KEY"
});

const res = await client.chat.completions.create({
  model: "claude-sonnet",
  messages: [{ role: "user", content: "Hello!" }]
});
console.log(res.choices[0].message.content);

curl — Image Background Removal

bash

curl -X POST https://apim-ai-apis.azure-api.net/v1/image/remove-background/base64 \
  -H "Ocp-Apim-Subscription-Key: YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"image\": \"$(base64 -i photo.jpg)\"}"

LLM Gateway — Popular Models

Model	Alias	Price ($/MTok in/out)
Claude Opus 4.6	`claude-opus`	$5 / $25
Claude Sonnet 4.6	`claude-sonnet`	$3 / $15
Claude Haiku 4.5	`claude-haiku`	$1 / $5
DeepSeek R1	`deepseek-r1`	$1.35 / $5.40
DeepSeek V3	`deepseek-v3`	$0.27 / $1.10
Llama 3.3 70B	`llama-3.3-70b`	$0.72 / $0.72
Amazon Nova Pro	`nova-pro`	$0.80 / $3.20
Amazon Nova Micro	`nova-micro`	$0.035 / $0.14
Mistral Large 3	`mistral-large-3`	$2 / $6
Qwen3 32B	`qwen3-32b`	$0.35 / $0.35

Full list: GET /v1/models (113+ models from 17 providers).

Supports: streaming SSE, tool calling, structured output (json_object/json_schema), extended thinking.

Works with: OpenAI SDK, LiteLLM, LangChain, Cline, Cursor, Aider, Continue, SillyTavern, Open WebUI.

MCP Servers (for AI Agents)

3 MCP servers with 20 tools total. Streamable HTTP transport.

Server	URL	Tools
Speech AI	`https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp`	10 tools + 8 resources + 3 prompts
NLP Tools	`https://apim-ai-apis.azure-api.net/mcp/nlp/mcp`	6 tools + 3 resources + 3 prompts
Image Tools	`https://apim-ai-apis.azure-api.net/mcp/image/mcp`	4 tools + 3 resources + 2 prompts

MCP Configuration (Claude Desktop / Cursor / Cline)

json

{
  "mcpServers": {
    "brainiall-speech": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    },
    "brainiall-nlp": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/nlp/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    },
    "brainiall-image": {
      "url": "https://apim-ai-apis.azure-api.net/mcp/image/mcp",
      "headers": { "Ocp-Apim-Subscription-Key": "YOUR_KEY" }
    }
  }
}

Also available on: Smithery (score 95/100) | MCPize | Apify ($0.02/call) | MCP Registry

Examples

File	Description
`python/basic_usage.py`	Speech APIs — assess, transcribe, synthesize
`python/pronunciation_tutor.py`	Interactive pronunciation tutor
`javascript/basic_usage.js`	Node.js examples for speech APIs
`curl/examples.sh`	curl commands for every endpoint
`mcp/claude-desktop-config.json`	MCP config for Claude Desktop
`mcp/cursor-config.json`	MCP config for Cursor IDE
`llms-full.txt`	Complete API reference for LLM consumption

Pricing

Product	Price	Unit
Pronunciation	$0.02	per call
TTS	$0.01-0.03	per 1K chars
STT (compact)	$0.01	per request
Whisper Pro	$0.02	per minute
NLP (any)	$0.001-0.002	per call
Image (any)	$0.003-0.005	per image
LLM Gateway	competitive pricing	per MTok

Credit packages: $5, $10, $25, $50, $100. Portal | Azure Marketplace (search "Brainiall").

License

MIT — Brainiall

Install

claude_desktop_config.json

{
  "mcpServers": {
    "speech-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://apim-ai-apis.azure-api.net/mcp/pronunciation/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.