BizCrush Developers

BizCrush API

AI-powered meeting platform API. Build your own speech-to-text service with real-time and batch transcription, manage meetings, AI summaries, and more.

Automatic language detection across 15 languages — no configuration required. Just send audio and get results.

Speech-to-Text API AI Integration & MCP

Use our APIs to build custom MCP servers, voice-powered apps, and AI workflows.

Get Your API Key

An API key is required to use BizCrush APIs. You can create up to 5 keys from your account settings.

Get API Key

Speech-to-Text API

Featured

Speech-to-Text API for audio transcription with speaker diarization. Supports file-based (batch) and real-time (streaming) transcription.

Build Your Own STT Service

Use the BizCrush STT API to build your own speech-to-text service. Integrate real-time transcription into your apps, process audio files at scale, or create custom voice-powered workflows — all with speaker diarization and multi-language support.

Automatic language detection across 15 languages — no configuration required. Just send audio and get results.

Overview

Base URL https://extapi.bizcrush.ai/v1

Authentication

All STT requests require an API key passed as a query parameter:

?api_key=YOUR_API_KEY

You can issue your API key at bizcru.sh/settings.

File STT

Send an audio file URL and receive the full transcript with speaker diarization.

POST /stt Auth: ?api_key

Transcribe an audio file URL and return the full transcript with speaker diarization.

Request Body (JSON)

Name Type Required Description
audio_url string required Public audio file URL (signed URL, CDN URL, etc.)
session_id string optional Session identifier. Auto-generated if omitted
enable_diarization boolean optional Enable speaker diarization (default: true)
language_hints string[] optional Language codes, e.g. ["ko","en"] or "ko,en". Up to 3; extras dropped. Omit for auto-detection. Legacy `language_hint` (single string) also accepted.

Response Fields

Field Type Description
text string Full transcript text
detected_language string Detected language code
confidence float Average confidence (0~1)
utterances array Speaker-diarized utterance segments
utterances[].speaker string Speaker number ("0", "1", "2", ...)
utterances[].text string Utterance text
utterances[].start_ms integer Start time (milliseconds)
utterances[].end_ms integer End time (milliseconds)
utterances[].confidence float Utterance confidence
utterances[].language string Utterance language

Response Example

{
  "text": "Could you introduce yourself and tell us about your role?",
  "detected_language": "en",
  "confidence": 0.961,
  "utterances": [
    {
      "speaker": "1",
      "text": "Could you introduce yourself and tell us about your role?",
      "start_ms": 960,
      "end_ms": 5400,
      "confidence": 0.94,
      "language": "en"
    },
    {
      "speaker": "2",
      "text": "Sure. My name is Ethan Kim, and I'm CTO of BizCrush.",
      "start_ms": 5820,
      "end_ms": 9600,
      "confidence": 0.96,
      "language": "en"
    }
  ]
}

cURL Example

curl -X POST \
  "https://extapi.bizcrush.ai/v1/stt?api_key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/audio.oga", "enable_diarization": true}'

Note: Response time depends on audio length — may take up to several minutes. Set timeout to 600+ seconds.

Live STT (WebSocket)

Real-time audio streaming transcription via WebSocket. Send audio chunks and receive interim/final results in real time.

WS wss://extapi.bizcrush.ai/v1/stt/stream

Query Parameters

Name Type Required Description
api_key string required API key
format string optional "json" for JSON text frames, omit for protobuf binary
reduce_noise string optional "true" to enable DeepFilter real-time noise reduction
language_hints string[] optional Language codes as comma-separated (?language_hints=ko,en) or repeated (?language_hints=ko&language_hints=en). Up to 3; extras dropped. Omit for auto-detection.

Protocol

1 Send Config

Send a JSON text frame with encoding and optional session_id

Field Type Description
encoding string "pcm16" or "opus" (default: "pcm16")
session_id string Session identifier (optional, auto-generated if omitted)
language_hints string[] Optional language codes, e.g. ["ko","en"] or "ko,en". Up to 3 entries; extras dropped. Overrides query param. Omit for auto-detection. 
{"encoding": "pcm16", "session_id": "optional-session-id"}
2 Receive Connection Status

Server responds with connection status

{"connected": true}
3 Stream Audio

Send raw audio as binary WebSocket frames

Encoding Format Chunk Size
pcm16 16kHz, mono, 16-bit little-endian 640 bytes (20ms) recommended
opus 16kHz, mono. Raw Opus packets or OGG/Opus container Opus frame unit
4 Receive Transcription Results

Server sends interim and final results as JSON text frames

Field Type Description
chunk.id string Chunk ID — same across interim/final for one utterance, new ID after final
chunk.session_id string Session ID
chunk.text string Transcribed text (cumulative — each interim contains full text so far)
chunk.is_final boolean false: interim result, true: final confirmed result 
{"chunk": {"id": "01KMCHP57H31XYZABC", "session_id": "my-session", "text": "Hello, how are you?", "is_final": true}}

Examples

Python

import asyncio
import json
import websockets

async def live_stt(api_key: str):
    url = f"wss://extapi.bizcrush.ai/v1/stt/stream?api_key={api_key}&format=json"

    async with websockets.connect(url) as ws:
        await ws.send(json.dumps({"encoding": "pcm16"}))

        resp = json.loads(await ws.recv())
        assert resp["connected"], f"Connection failed: {resp}"

        async def send_audio():
            with open("audio.pcm", "rb") as f:
                while chunk := f.read(640):
                    await ws.send(chunk)
                    await asyncio.sleep(0.02)
            await asyncio.sleep(3)
            await ws.close()

        async def receive_results():
            try:
                async for msg in ws:
                    data = json.loads(msg)
                    if "chunk" in data:
                        chunk = data["chunk"]
                        status = "FINAL" if chunk["is_final"] else "interim"
                        print(f"[{status}] {chunk['text']}")
            except websockets.exceptions.ConnectionClosed:
                pass

        await asyncio.gather(send_audio(), receive_results())

asyncio.run(live_stt("YOUR_API_KEY"))

JavaScript (Browser)

const ws = new WebSocket(
  "wss://extapi.bizcrush.ai/v1/stt/stream?api_key=YOUR_API_KEY&format=json"
);

ws.onopen = () => {
  ws.send(JSON.stringify({ encoding: "pcm16" }));
};

ws.onmessage = (event) => {
  const data = JSON.parse(event.data);

  if (data.connected) {
    console.log("Connected! Start sending audio...");
  }

  if (data.chunk) {
    const { id, text, is_final } = data.chunk;
    console.log(`[${is_final ? "FINAL" : "interim"}] ${text}`);
  }
};

function sendAudioChunk(pcmData) {
  if (ws.readyState === WebSocket.OPEN) {
    ws.send(pcmData);
  }
}

Text-to-Speech (TTS)

Convert text to natural-sounding speech and receive a signed download URL (audio uploaded to Firebase Storage).

POST /tts Auth: ?api_key

Generate speech audio from text and return a signed download URL (audio uploaded to Firebase Storage at tts/{session_id}/{message_id}.ogg).

Request Body (Protobuf)

application/x-protobuf (request and response are protobuf-encoded SessionTTSRequest / SessionTTSResponse)

Name Type Required Description
session_id string required Session identifier
message_id string required Message identifier (used in storage path)
text string required Text to convert to speech

Response Fields

Field Type Description
audio_url string Signed download URL (Opus / OGG) — valid for several days
error string Set on failure; audio_url empty
Audio Format
OGG/Opus, single channel
Default Voice
nova (configurable server-side)

Supported Languages

Automatic language detection is built in — no configuration needed. The STT engine detects and transcribes across 15 languages seamlessly, even when speakers switch languages mid-conversation. Optionally use language_hint for faster detection.

Code Language
en English
zh 中文
hi हिन्दी
es Español
ar العربية
fr Français
pt Português
ru Русский
id Bahasa Indonesia
de Deutsch
ja 日本語
vi Tiếng Việt
it Italiano
ko 한국어
th ภาษาไทย

STT Error Codes

Status Error Description
401 Missing authorization API key not provided
401 Invalid API key Invalid API key
400 Empty request body Request body is empty
400 Missing audio_url audio_url field missing (File STT)
400 Missing session_id, message_id, or text Required TTS field missing
400 Invalid JSON JSON parsing failed
500 TTS generation failed OpenAI TTS call failed
500 Storage upload failed Firebase Storage upload failed
500 (varies) Internal server error (transcription failure, etc.)
WS 1008 Auth failure WebSocket closed with code 1008 on authentication failure

Meeting REST API

Authentication

All API requests require an X-API-Key header.

curl -X POST https://extapi.bizcrush.ai/v1/get-meetings \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{}'

You can issue your API key at bizcru.sh/settings.

Quick Start

Create a meeting and invite a participant in one request:

curl -X POST https://extapi.bizcrush.ai/v1/create-meeting \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
    "participant_ids": ["em:john@example.com"],
    "title": "Weekly Standup"
  }'

Response:

{
  "meeting": {
    "id": "01KNGVN84KR7T5CVDY9TTW7FFW",
    "host_user_id": "0J56UlxXAS",
    "participant_ids": ["0J56UlxXAS", "em:john@example.com"],
    "status": "MS_LIVE",
    "title": "Weekly Standup",
    "language": "ko",
    "translation_languages": ["ko", "en"]
  }
}

Meetings

Create, delete, and list meetings.

POST /v1/create-meeting

Create a new meeting and optionally invite participants.

Parameters

Name Type Required Description
participant_ids list[str] optional Participant IDs. Formats: userId (no prefix), em:email@example.com
title str optional Meeting title
POST /v1/delete-meeting

Delete a meeting by ID.

Parameters

Name Type Required Description
meeting_id str required Meeting ID to delete
POST /v1/get-meetings

List the authenticated user's meetings, newest first.

Parameters

Name Type Required Description
last_updated_at str optional Pagination cursor: fetch meetings updated before this time (RFC 3339)
limit int optional Max results per page (default: 50, max: 50)

Meeting Messages

Send, delete, and list meeting messages (text, summaries, etc.).

POST /v1/send-meeting-message

Send a text message to a meeting.

Parameters

Name Type Required Description
meeting_message dict required Meeting message object with meeting_id and text fields
POST /v1/delete-meeting-message

Delete a message from a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
message_id str required Message ID to delete
POST /v1/get-meeting-messages

Get messages for a meeting (summaries, user messages, etc.).

Parameters

Name Type Required Description
meeting_id str required Meeting ID
last_updated_at str optional Pagination cursor (RFC 3339)
limit int optional Max results per page (default: 50)

Meeting AI

AI-powered meeting summarization and Q&A.

POST /v1/summarize-meeting

Generate an AI summary of a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID to summarize
send_email_to_participants bool optional Send summary email to participants (default: false)
user_prompt str optional Custom prompt to guide summarization
POST /v1/ask-ai-for-meeting

Ask AI a question about a meeting's content.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
message dict required User question as {text: '...'} object
model int optional LLM model enum value (0 = default)
attachment_urls list[str] optional Attachment URLs (PDF, images, etc.)
source_content str optional Existing markdown to edit (edit mode)
source_document_id str optional Document ID for version chaining

Meeting Cached Data

Retrieve cached meeting summaries and transcripts.

POST /v1/get-meeting-summary

Get the AI-generated summary of a meeting (cached).

Parameters

Name Type Required Description
meeting_id str required Meeting ID
force_refresh bool optional Force refresh from DB instead of cache
POST /v1/get-meeting-transcripts

Get the full transcripts of a meeting (cached).

Parameters

Name Type Required Description
meeting_id str required Meeting ID
force_refresh bool optional Force refresh from DB instead of cache

Meeting Participants

Add/remove participants and manage co-host roles.

POST /v1/add-meeting-participants

Add participants to a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
participant_ids list[str] required Participant IDs. Formats: userId, em:email@example.com
POST /v1/remove-meeting-participants

Remove participants from a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
participant_ids list[str] required Participant IDs to remove
POST /v1/assign-co-host

Assign co-host role to users in a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
user_ids list[str] required User IDs to assign as co-host
POST /v1/remove-co-host

Remove co-host role from users in a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
user_ids list[str] required User IDs to remove co-host from

Meeting Settings

Get and update default meeting settings (languages, keywords).

POST /v1/get-user-default-meeting-setting

Get the user's default meeting settings.

Parameters

Name Type Required Description
device_language_code str optional IETF BCP-47 language code (default: 'en')
POST /v1/update-user-default-meeting-setting

Update the user's default meeting settings.

Parameters

Name Type Required Description
original_languages list[str] optional STT input languages (IETF BCP-47)
view_language str optional Document generation language (default: 'en')
translation_languages list[str] optional Translation target languages
contextual_keywords list[str] optional Keywords to help AI understand meeting context

Transcription

Access live transcription chunks, finalized utterances, and corrections.

POST /v1/get-live-transcription-chunks

Get real-time transcription chunks for a meeting.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
last_updated_at str required Pagination cursor (RFC 3339). Use '1970-01-01T00:00:00Z' for first page
message_id str optional Filter by message ID
limit int optional Max results (default: 100)
POST /v1/get-transcript-utterances

Get finalized transcript utterances with confidence scores.

Parameters

Name Type Required Description
meeting_id str required Meeting ID
last_updated_at str required Pagination cursor (RFC 3339). Use '1970-01-01T00:00:00Z' for first page
message_id str optional Filter by message ID
limit int optional Max results (default: 100)
POST /v1/update-transcript-utterance

Correct a transcribed utterance's text.

Parameters

Name Type Required Description
id str required Utterance document ID
meeting_id str required Meeting ID
transcript str required Corrected transcript text

Notion

Upload meeting summaries to Notion.

POST /v1/upload-meeting-to-notion

Upload a meeting summary to a Notion workspace.

Parameters

Name Type Required Description
user_id str required User ID (for retrieving Notion access token)
meeting_id str required Meeting ID to upload

People

List contacts and people.

POST /v1/get-my-people

List the authenticated user's contacts.

Parameters

Name Type Required Description
cursor str optional Pagination cursor (name:email format)
limit int optional Results per page (default: 20)

Error Handling

The API returns standard HTTP status codes with JSON error bodies:

Status Description
401 Invalid or missing API key
400 Invalid request body (validation error)
404 Resource not found (invalid meeting/message ID)
500 Internal server error 
{
  "success": false,
  "error": "Meeting not found",
  "code": "NOT_FOUND"
}

Zapier Integration

Overview

Connect BizCrush with your favorite tools through our Zapier integration. Automatically capture meeting summaries, generate AI documents, and push insights to Slack, Notion, Google Docs, and more.

Base URL https://bizcru.sh

Triggers

4 polling triggers that detect new meetings, summaries, contacts, and follow-up emails.

Actions

2 actions to retrieve meeting details and generate AI documents with custom prompts.

Authentication

Zapier uses OAuth 2.0 (Authorization Code flow). The token lifecycle is managed automatically by Zapier.

OAuth 2.0 Flow

Step Description Endpoint
1 Authorization — User is redirected to BizCrush to grant access GET /oauth/zapier/authorize
2 Token Exchange — Authorization code is exchanged for access and refresh tokens POST /api/oauth/zapier/token
3 API Requests — Access token is sent as a Bearer token Authorization: Bearer <access_token>

Test Connection

GET /api/zapier/me Auth: Bearer Token 
curl https://bizcru.sh/api/zapier/me \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"

Response Example

{
  "user_id": "abc123",
  "email": "user@example.com",
  "display_name": "John Doe"
}

Triggers

Polling-based triggers. Zapier calls these periodically to detect new data. All triggers return arrays sorted by date (newest first), max 50 items.

GET /api/zapier/triggers/meeting-ended Auth: Bearer Token

Meeting Ended

Fires when a meeting you participated in has ended. Returns up to 50 recent ended meetings.

Response Fields

Field Type Description
id string Meeting ID (deduplication key)
title string Meeting title
start_at ISO 8601 Meeting start time
end_at ISO 8601 Meeting end time
language string Meeting language (e.g., "ko", "en")
host_user_id string Host user ID
participant_count number Number of participants
tags string[] Meeting tags

Response Example

[
  {
    "id": "01KMHVN8JX62M7HPS2H4GNXVR8",
    "title": "Weekly Standup",
    "start_at": "2025-01-15T09:00:00.000Z",
    "end_at": "2025-01-15T10:30:00.000Z",
    "language": "en",
    "host_user_id": "abc123",
    "participant_count": 3,
    "tags": ["standup", "weekly"]
  }
]
GET /api/zapier/triggers/summary-ready Auth: Bearer Token

Summary Ready

Fires when an AI-generated summary is ready for one of your meetings.

Response Fields

Field Type Description
id string Summary message ID (deduplication key)
meeting_id string Meeting ID
meeting_title string Meeting title
ai_model string AI model used for generation
markdown_body string Summary content in Markdown
created_at ISO 8601 Summary creation time

Response Example

[
  {
    "id": "summary_msg_id",
    "meeting_id": "01KMHVN8JX62M7HPS2H4GNXVR8",
    "meeting_title": "Weekly Standup",
    "ai_model": "gpt-4o",
    "markdown_body": "## Meeting Summary\n- Discussed project updates...",
    "created_at": "2025-01-15T10:35:00.000Z"
  }
]
GET /api/zapier/triggers/contact-discovered Auth: Bearer Token

Contact Discovered

Fires when a new contact (guest profile) is discovered from a meeting.

Response Fields

Field Type Description
id string Contact message ID (deduplication key)
meeting_id string Meeting ID
meeting_title string Meeting title
name string Contact name
email string Contact email
company_name string Company name
company_position string Job title / position
linkedin_id string LinkedIn profile ID
created_at ISO 8601 Discovery time

Response Example

[
  {
    "id": "contact_msg_id",
    "meeting_id": "01KMHVN8JX62M7HPS2H4GNXVR8",
    "meeting_title": "Sales Call",
    "name": "John Doe",
    "email": "john@example.com",
    "company_name": "Acme Inc",
    "company_position": "CEO",
    "linkedin_id": "johndoe",
    "created_at": "2025-01-15T11:00:00.000Z"
  }
]
GET /api/zapier/triggers/followup-email-ready Auth: Bearer Token

Follow-up Email Ready

Fires when an AI-generated follow-up email is ready for a meeting.

Response Fields

Field Type Description
id string Email message ID (deduplication key)
meeting_id string Meeting ID
meeting_title string Meeting title
subject string Email subject line
body_html string Email body in HTML
created_at ISO 8601 Email generation time

Response Example

[
  {
    "id": "email_msg_id",
    "meeting_id": "01KMHVN8JX62M7HPS2H4GNXVR8",
    "meeting_title": "Sales Call",
    "subject": "Follow up from our meeting",
    "body_html": "<p>Thank you for the meeting.</p>",
    "created_at": "2025-01-15T11:10:00.000Z"
  }
]

Actions

Actions that Zapier users can trigger in their Zaps.

GET /api/zapier/meetings/{id} Auth: Bearer Token

Get Meeting Details

Retrieve detailed information about a specific meeting, including its latest AI summary.

Path Parameters

Parameter Required Description
id required Meeting ID

Response Example

{
  "id": "01KMHVN8JX62M7HPS2H4GNXVR8",
  "title": "Q1 Planning Meeting",
  "start_at": "2025-01-15T09:00:00.000Z",
  "end_at": "2025-01-15T10:30:00.000Z",
  "language": "en",
  "host_user_id": "abc123",
  "participant_count": 4,
  "tags": ["planning", "q1"],
  "latest_summary": {
    "ai_model": "gpt-4o",
    "markdown_body": "## Key Decisions\n- Approved Q1 budget...",
    "created_at": "2025-01-15T10:35:00.000Z"
  }
}
POST /api/zapier/meetings/{id}/generate-document Auth: Bearer Token

Generate AI Document

Generate an AI document from a meeting using a custom prompt. Supports asynchronous callback delivery for long-running generations.

Path Parameters

Parameter Required Description
id required Meeting ID

Request Body

Field Type Required Default Description
prompt str required — Custom prompt for document generation (e.g., "Summarize key decisions and action items")
model str optional gpt-4o AI model — gpt-4o (default) or claude
callback_url str optional — URL to receive async results (used by Zapier automatically)

Response Example

// Sync response (no callback)
{
  "success": true,
  "meeting_id": "01KMHVN8...",
  "document_text": "## Summary\n...",
  "message": "AI document generation requested."
}

Async Callback Response

// Async: initial response (immediate)
{
  "success": true,
  "meeting_id": "01KMHVN8...",
  "message": "AI document generation started. Result will be delivered via callback."
}

// Async: callback POST to callback_url (after AI completes)
{
  "status": "success",
  "meeting_id": "01KMHVN8...",
  "document_text": "# Detailed AI Document\n\n## Key Decisions\n- ...",
  "created_at": "2025-01-15T10:40:00.000Z"
}