---
schema: "interfacedelta-service-md/1"
target_key: "sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69"
origin: "https://api.brainiall.com"
protocols: ["mcp"]
observed_at: "2026-11-14T08:01:15.534Z"
generated_at: "2026-11-14T10:09:56.175Z"
record_url: "https://interfacedelta.com/atlas/sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69"
record_api: "https://interfacedelta.com/api/v1/record/services/sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69"
source: "InterfaceDelta atlas"
license_note: "Use of this record is governed by https://interfacedelta.com/terms."
---

# Service record: https://api.brainiall.com

## Identity
- Origin: https://api.brainiall.com
- Endpoints: https://api.brainiall.com/mcp/pronunciation/mcp
- Protocols: mcp
- Registry names: com.brainiall/pronunciation
- First retained observation: 2026-11-14T08:01:15.534Z
- Latest observation: 2026-11-14T08:01:15.534Z

## Tools
MCP tools, OpenAPI operations, WebMCP tools and A2A skills; excludes prompts and resources.
Total capabilities: 14; non-tool capabilities: 0.
- Tool 1: assess\_pronunciation (mcp); inputs: audio\_base64, audio\_format, text; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 2: check\_pronunciation\_service (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 3: check\_stt\_service (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 4: check\_tts\_service (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 5: check\_whisper\_service (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 6: get\_phoneme\_inventory (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}
- Tool 7: list\_tts\_voices (mcp); inputs: none shown; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 8: synthesize\_speech (mcp); inputs: speed, text, voice; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 9: transcribe\_audio (mcp); inputs: audio\_base64, audio\_format, include\_timestamps; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 10: transcribe\_audio\_pro (mcp); inputs: audio\_base64, diarize, language; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 11: voice\_id\_enroll (mcp); inputs: audio, group\_id, speaker\_id; inputs omitted: 0; annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}
- Tool 12: voice\_id\_identify (mcp); inputs: audio, group\_id, top\_k; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 13: voice\_id\_list\_speakers (mcp); inputs: group\_id; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
- Tool 14: voice\_id\_verify (mcp); inputs: audio, group\_id, speaker\_id, threshold; inputs omitted: 0; annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}
Tools omitted: 0.

## Effect readings (AI)
- Tool 1 purpose: ◇ AI reading; Assesses spoken English pronunciation from audio against reference text, returning overall, sentence, word and phoneme scores.; lens: tool-purpose-v1; model: not recorded.
- Tool 2 (check\_pronunciation\_service): ◇ AI reading; state: counted; reads (confidence 0.8); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 2 purpose: ◇ AI reading; Checks whether the pronunciation scoring service is up, reporting its status, whether its model is loaded, and its API version.; lens: tool-purpose-v1; model: not recorded.
- Tool 3 purpose: ◇ AI reading; Checks whether the speech recognition service is up, reporting its status, whether the model is loaded, and the API version.; lens: tool-purpose-v1; model: not recorded.
- Tool 5 (check\_whisper\_service): ◇ AI reading; state: counted; reads (confidence 0.8); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 5 purpose: ◇ AI reading; Checks whether the speech transcription service and its diarization pipeline are loaded and ready.; lens: tool-purpose-v1; model: not recorded.
- Tool 6 (get\_phoneme\_inventory): ◇ AI reading; state: counted; reads (confidence 0.8); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 6 purpose: ◇ AI reading; Lists every English phoneme the pronunciation scorer can evaluate, with ARPAbet and IPA symbols, examples, and categories.; lens: tool-purpose-v1; model: not recorded.
- Tool 7 (list\_tts\_voices): ◇ AI reading; state: counted; reads (confidence 0.88); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 7 purpose: ◇ AI reading; Lists the text-to-speech voices on offer, with each voice's id, name, gender, accent and grade, plus the default voice ID.; lens: tool-purpose-v1; model: not recorded.
- Tool 8 purpose: ◇ AI reading; Converts English text into a spoken WAV clip in one of twelve voices, returned as base64 audio with metadata.; lens: tool-purpose-v1; model: not recorded.
- Tool 9 purpose: ◇ AI reading; Returns a text transcript of base64-encoded English speech audio, with optional per-word timestamps and confidence scores.; lens: tool-purpose-v1; model: not recorded.
- Tool 10 purpose: ◇ AI reading; Returns a multilingual transcript of base64-encoded audio with word timestamps, confidence scores, and optional speaker labels.; lens: tool-purpose-v1; model: not recorded.
- Tool 11 (voice\_id\_enroll): ◇ AI reading; state: counted; creates (confidence 0.855); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 11 purpose: ◇ AI reading; Registers a speaker's voice profile from a short audio clip, storing only an irreversible embedding, not the raw recording.; lens: tool-purpose-v1; model: not recorded.
- Tool 12 (voice\_id\_identify): ◇ AI reading; state: counted; reads (confidence 0.8); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 12 purpose: ◇ AI reading; Returns enrolled speakers in a group ranked by voice similarity to a given audio clip, best match first.; lens: tool-purpose-v1; model: not recorded.
- Tool 13 (voice\_id\_list\_speakers): ◇ AI reading; state: counted; reads (confidence 0.87); lens: side-effects@1; model: claude-haiku-5.5.
- Tool 13 purpose: ◇ AI reading; Lists voice profiles stored under a given group ID, with sample counts for each speaker.; lens: tool-purpose-v1; model: not recorded.
- Tool 14 purpose: ◇ AI reading; Verifies whether an audio clip matches a previously enrolled speaker, returning a similarity score and match result.; lens: tool-purpose-v1; model: not recorded.

## Change history
No changes recorded in the retained history.

## Payment rails
- Protocols observed: none.
- HTTP 402 seen in retained observations: false.

## Not covered
- We don't call tools.
- We don't rate or certify.
- We don't publish prices.
- We cover only what was observed.

## Evidence
- Identity: observed / declared; observation time: 2026-11-14T08:01:15.534Z.
- Tools: declared; observation time: 2026-11-14T08:01:15.534Z.
- Effect readings (AI): AI reading; observation time: 2026-11-14T08:01:15.534Z.
- Change history: observed; observation time: 2026-11-14T08:01:15.534Z; change observation times: none.
- Payment rails: observed; observation time: 2026-11-14T08:01:15.534Z.

```json
{
  "schema": "interfacedelta-service-md/1",
  "target_key": "sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69",
  "origin": "https://api.brainiall.com",
  "protocols": [
    "mcp"
  ],
  "observed_at": "2026-11-14T08:01:15.534Z",
  "generated_at": "2026-11-14T10:09:56.175Z",
  "record_url": "https://interfacedelta.com/atlas/sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69",
  "record_api": "https://interfacedelta.com/api/v1/record/services/sha256:1ce8d6d23432f5359a545700b3ddceaddff4cce5460a28cc30bf8206a2317e69",
  "source": "InterfaceDelta atlas",
  "license_note": "Use of this record is governed by https://interfacedelta.com/terms.",
  "identity": {
    "origin": "https://api.brainiall.com",
    "endpoints": [
      "https://api.brainiall.com/mcp/pronunciation/mcp"
    ],
    "protocols": [
      "mcp"
    ],
    "registry_names": [
      "com.brainiall/pronunciation"
    ],
    "first_retained_observation": "2026-11-14T08:01:15.534Z",
    "latest_observation": "2026-11-14T08:01:15.534Z"
  },
  "tools": [
    {
      "name": "assess_pronunciation",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio_base64",
        "audio_format",
        "text"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Assesses spoken English pronunciation from audio against reference text, returning overall, sentence, word and phoneme scores.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "check_pronunciation_service",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.8
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Checks whether the pronunciation scoring service is up, reporting its status, whether its model is loaded, and its API version.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "check_stt_service",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Checks whether the speech recognition service is up, reporting its status, whether the model is loaded, and the API version.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "check_tts_service",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null
    },
    {
      "name": "check_whisper_service",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.8
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Checks whether the speech transcription service and its diarization pipeline are loaded and ready.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "get_phoneme_inventory",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": false
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.8
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Lists every English phoneme the pronunciation scorer can evaluate, with ARPAbet and IPA symbols, examples, and categories.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "list_tts_voices",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.88
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Lists the text-to-speech voices on offer, with each voice's id, name, gender, accent and grade, plus the default voice ID.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "synthesize_speech",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "speed",
        "text",
        "voice"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Converts English text into a spoken WAV clip in one of twelve voices, returned as base64 audio with metadata.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "transcribe_audio",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio_base64",
        "audio_format",
        "include_timestamps"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Returns a text transcript of base64-encoded English speech audio, with optional per-word timestamps and confidence scores.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "transcribe_audio_pro",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio_base64",
        "diarize",
        "language"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Returns a multilingual transcript of base64-encoded audio with word timestamps, confidence scores, and optional speaker labels.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "voice_id_enroll",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio",
        "group_id",
        "speaker_id"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": false,
        "destructiveHint": false,
        "idempotentHint": false,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "creates",
            "confidence": 0.855
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Registers a speaker's voice profile from a short audio clip, storing only an irreversible embedding, not the raw recording.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "voice_id_identify",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio",
        "group_id",
        "top_k"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.8
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Returns enrolled speakers in a group ranked by voice similarity to a given audio clip, best match first.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "voice_id_list_speakers",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "group_id"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": {
        "marker": "◇ AI reading",
        "state": "counted",
        "classes": [
          {
            "class": "reads",
            "confidence": 0.87
          }
        ],
        "lens": "side-effects@1",
        "model": "claude-haiku-5.5"
      },
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Lists voice profiles stored under a given group ID, with sample counts for each speaker.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    },
    {
      "name": "voice_id_verify",
      "kind": "mcp.tool",
      "protocol": "mcp",
      "inputs": [
        "audio",
        "group_id",
        "speaker_id",
        "threshold"
      ],
      "inputs_omitted": 0,
      "annotations": {
        "readOnlyHint": true,
        "destructiveHint": false,
        "idempotentHint": true,
        "openWorldHint": true
      },
      "effects": null,
      "purpose": {
        "marker": "◇ AI reading",
        "text": "Verifies whether an audio clip matches a previously enrolled speaker, returning a similarity score and match result.",
        "lens": "tool-purpose-v1",
        "model": null
      }
    }
  ],
  "capability_count": 14,
  "non_tool_capability_count": 0,
  "tool_count_scope": "MCP tools, OpenAPI operations, WebMCP tools and A2A skills; excludes prompts and resources.",
  "tools_omitted": 0,
  "tools_state": "recorded",
  "changes": [],
  "payment_rails": {
    "protocols": [],
    "http_402_seen": false
  },
  "not_covered": [
    "We don't call tools.",
    "We don't rate or certify.",
    "We don't publish prices.",
    "We cover only what was observed."
  ],
  "evidence": [
    {
      "section": "Identity",
      "classes": [
        "observed",
        "declared"
      ],
      "observed_at": "2026-11-14T08:01:15.534Z"
    },
    {
      "section": "Tools",
      "classes": [
        "declared"
      ],
      "observed_at": "2026-11-14T08:01:15.534Z"
    },
    {
      "section": "Effect readings (AI)",
      "classes": [
        "AI reading"
      ],
      "observed_at": "2026-11-14T08:01:15.534Z"
    },
    {
      "section": "Change history",
      "classes": [
        "observed"
      ],
      "observed_at": "2026-11-14T08:01:15.534Z",
      "observation_times": []
    },
    {
      "section": "Payment rails",
      "classes": [
        "observed"
      ],
      "observed_at": "2026-11-14T08:01:15.534Z"
    }
  ]
}
```