Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
All 92 tools →
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/pipeshub:pipeshub-conversational-speech-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Pipeshub Conversational Speech API
version: 1.0.0
contact:
name: API Support
email: support@pipeshub.com
description: 'Operations tagged Conversational Speech across 2 of this provider''s published API definitions: pipeshub-openapi.yaml, pipeshub-openapi.yml. Each path carries the servers of the definition it was published in.'
servers:
- url: '{instance_url}/api/v1'
description: Base API URL
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL (without /api/v1)
- url: '{instance_url}'
description: Root URL (used for MCP endpoints mounted at /mcp)
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL
security:
- bearerAuth: []
- oauth2: []
tags:
- name: Conversational Speech
description: 'Server-backed Speech-to-Text (STT) and Text-to-Speech (TTS) for the chat UI.
These endpoints are used by the chat frontend when an admin has configured a
TTS/STT provider under the AI Models configuration. When no provider is
configured the client falls back to the browser''s native Web Speech API, so
callers should treat a `409` response as "unconfigured, use browser APIs"
rather than as a fatal error.'
paths:
/chat/transcribe:
post:
tags:
- Conversational Speech
summary: Transcribe an audio clip (Speech-to-Text)
description: 'Upload a short audio recording and receive its transcript from the
configured Speech-to-Text provider (OpenAI Whisper, `gpt-4o-transcribe`,
a self-hosted `faster-whisper` model, Wispr Flow, or Gemini multimodal
models such as `gemini-2.5-flash`).
Overview:
The chat UI captures audio via the browser''s `MediaRecorder` and
POSTs it here as `multipart/form-data`. If no STT provider is
configured the endpoint returns 409 and the client falls
back to the browser''s native Web Speech Recognition.
Limits:
Audio payload is capped at 25 MB (matches OpenAI''s
audio.transcriptions.create limit).
Supported MIME types include audio/webm,
audio/ogg, audio/mp4,
audio/mpeg, audio/wav, and
audio/flac.'
operationId: transcribeChatAudio
security:
- bearerAuth: []
- oauth2:
- conversation:chat
requestBody:
required: true
description: Audio clip (multipart/form-data) to transcribe, with an optional language hint.
content:
multipart/form-data:
schema:
type: object
required:
- file
properties:
file:
type: string
format: binary
description: 'Recorded audio clip. Must be ≤ 25 MB. Supported MIME
types include `audio/webm`, `audio/ogg`, `audio/mp4`,
`audio/m4a`, `audio/mpeg`, `audio/wav`, and
`audio/flac`. The browser''s `MediaRecorder` default
(`audio/webm;codecs=opus`) is recommended.
'
language:
type:
- string
- 'null'
description: 'Optional ISO-639-1 language hint forwarded to the
provider (e.g. `en`, `fr`). When omitted the provider
auto-detects. The `wispr` provider treats this as a
property hint; Gemini appends it to the transcription
prompt.
'
example: en
responses:
'200':
description: Transcription succeeded.
content:
application/json:
schema:
$ref: '#/components/schemas/TranscriptionResponse'
examples:
openai:
summary: OpenAI `gpt-4o-mini-transcribe`
value:
text: Turn on the office lights.
provider: openAI
model: gpt-4o-mini-transcribe
wispr:
summary: Wispr Flow
value:
text: Summarize today's standup notes.
provider: wispr
model: flow
gemini:
summary: Gemini multimodal
value:
text: Create a ticket to fix the login bug.
provider: gemini
model: gemini-2.5-flash
'400':
description: Empty audio payload (`file` read returned 0 bytes).
'401':
description: Unauthorized — valid bearer token required.
'409':
description: 'No Speech-to-Text provider is configured. The client should fall
back to the browser Web Speech API.
'
'413':
description: 'Audio payload exceeds the 25 MB limit. This matches OpenAI''s
`audio.transcriptions.create` ceiling and the soft cap enforced
by the node proxy (`multer` `fileSize`).
'
'500':
description: 'Runtime error — for example the optional `faster-whisper`
package is not installed for the `whisper` provider, or
`ffmpeg` is missing on the host for the `wispr` provider
(required to transcode audio to 16 kHz WAV).
'
'502':
description: Upstream provider failure (message is intentionally generic; see server logs for details).
servers:
- url: '{instance_url}/api/v1'
description: Base API URL
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL (without /api/v1)
- url: '{instance_url}'
description: Root URL (used for MCP endpoints mounted at /mcp)
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL
/chat/speak:
post:
tags:
- Conversational Speech
summary: Synthesize audio for a message (Text-to-Speech)
description: 'Generate audio for the supplied text using the configured Text-to-Speech
provider (e.g. OpenAI `tts-1`, `gpt-4o-mini-tts`, or Gemini
`gemini-3.1-flash-tts-preview` / `gemini-2.5-flash-preview-tts`).
The response body is
the raw audio bytes in the requested format.
Overview:
The chat UI calls this when the user clicks "Read aloud" on an
assistant message. If no TTS provider is configured the endpoint
returns 409 and the client falls back to the browser''s
speechSynthesis API.
Limits:
Input text is capped at 4096 characters.
speed is clamped to the range
[0.25, 4.0].
Unknown format values silently fall back to
mp3.'
operationId: synthesizeChatSpeech
security:
- bearerAuth: []
- oauth2:
- conversation:chat
requestBody:
required: true
description: Text to synthesize and optional voice, format, and speed parameters.
content:
application/json:
schema:
$ref: '#/components/schemas/SpeakRequest'
responses:
'200':
description: 'Raw audio bytes in the negotiated format. Response headers
<code>X-TTS-Provider</code> and <code>X-TTS-Model</code> identify
the provider/model that produced the audio.
'
headers:
X-TTS-Provider:
schema:
type: string
description: Provider id that produced the audio.
X-TTS-Model:
schema:
type: string
description: Model id that produced the audio.
Cache-Control:
schema:
type: string
description: Always <code>no-store</code>.
content:
audio/mpeg:
schema:
type: string
format: binary
audio/ogg:
schema:
type: string
format: binary
audio/aac:
schema:
type: string
format: binary
audio/flac:
schema:
type: string
format: binary
audio/wav:
schema:
type: string
format: binary
audio/pcm:
schema:
type: string
format: binary
'400':
description: Request body missing or `text` is empty / whitespace.
'401':
description: Unauthorized — valid bearer token required.
'409':
description: 'No Text-to-Speech provider is configured. The client should fall
back to the browser Web Speech API.
'
'413':
description: Text exceeds the 4096-character limit.
'502':
description: Upstream provider failure.
servers:
- url: '{instance_url}/api/v1'
description: Base API URL
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL (without /api/v1)
- url: '{instance_url}'
description: Root URL (used for MCP endpoints mounted at /mcp)
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL
/chat/speech/capabilities:
get:
tags:
- Conversational Speech
summary: Report configured TTS/STT providers
description: 'Lightweight probe that tells the chat UI whether to use the server
speech routes or the browser Web Speech API. Only public provider
metadata is returned; API keys and organization ids are never
exposed.'
operationId: getChatSpeechCapabilities
security:
- bearerAuth: []
- oauth2:
- conversation:chat
responses:
'200':
description: Current TTS/STT capability summary.
content:
application/json:
schema:
$ref: '#/components/schemas/SpeechCapabilitiesResponse'
'401':
description: Unauthorized — valid bearer token required.
servers:
- url: '{instance_url}/api/v1'
description: Base API URL
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL (without /api/v1)
- url: '{instance_url}'
description: Root URL (used for MCP endpoints mounted at /mcp)
variables:
instance_url:
default: https://app.pipeshub.com
description: Base server URL
components:
schemas:
SpeechCapabilitiesResponse:
type: object
description: 'Reports whether the server has a TTS/STT provider configured. When a
bucket is `null` the chat UI falls back to the browser''s Web Speech
API for that capability.
'
properties:
tts:
allOf:
- $ref: '#/components/schemas/SpeechCapabilitySummary'
stt:
allOf:
- $ref: '#/components/schemas/SpeechCapabilitySummary'
TranscriptionResponse:
type: object
description: 'Result of a successful call to `/chat/transcribe`. The server
always includes the provider and model that handled the request
so the client can display / log which backend produced the
transcript.
'
required:
- text
- provider
- model
properties:
text:
type: string
description: 'Transcribed text. May be an empty string for silence,
unintelligible audio, or when the provider returned no
content.
'
example: Turn on the office lights.
provider:
type: string
description: 'Provider id that handled the transcription. One of
`openAI`, `whisper` (self-hosted `faster-whisper`),
`wispr` (Wispr Flow), or `gemini`.
'
enum:
- openAI
- whisper
- wispr
- gemini
example: openAI
model:
type: string
description: 'Model id that handled the transcription. Examples:
`whisper-1`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`,
`base`/`small`/`medium`/`large-v3` for self-hosted
`faster-whisper`, `flow` for Wispr, or `gemini-2.5-flash` /
`gemini-2.5-pro` for Gemini multimodal.
'
example: gpt-4o-mini-transcribe
SpeakRequest:
type: object
required:
- text
properties:
text:
type: string
minLength: 1
maxLength: 4096
description: 'UTF-8 text to synthesize. Capped at 4096 characters to match the
underlying provider limit (OpenAI TTS) and avoid unbounded cost.
'
example: Hello, this is a PipesHub voice test.
voice:
type:
- string
- 'null'
description: 'Provider voice override. If omitted, the voice configured by the
admin for the active TTS provider is used. For OpenAI: one of
`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`.
'
example: alloy
format:
type:
- string
- 'null'
enum:
- mp3
- opus
- aac
- flac
- wav
- pcm
description: 'Audio response format. Unknown values are silently coerced to
`mp3` server-side.
'
example: mp3
speed:
type:
- number
- 'null'
format: float
minimum: 0.25
maximum: 4.0
description: 'Playback speed multiplier. Values outside the documented range
are clamped server-side.
'
example: 1.0
SpeechCapabilitySummary:
type: object
description: 'Public summary of an active speech provider. Secrets (api keys,
organization ids, etc.) are never included. The server always picks
the config flagged `isDefault` in `aiModels`; when no entry is
flagged, the first configured entry is used and `isDefault` is
reported as `false` so the chat UI can surface the fallback.
'
required:
- provider
properties:
provider:
type: string
description: Provider id (e.g. `openAI`, `gemini`, `whisper`, `wispr`).
example: openAI
model:
type:
- string
- 'null'
description: 'Active (default) model id the server will dispatch to. Same
value as `defaultModel`; retained for backwards compatibility
with older chat clients.
'
example: gpt-4o-mini-tts
defaultModel:
type:
- string
- 'null'
description: 'Model id the server will use when no explicit `model` is passed
to `/chat/speak` or `/chat/transcribe`. Chosen as the first
entry from the configured comma-separated `configuration.model`
list.
'
example: gpt-4o-mini-tts
models:
type: array
items:
type: string
description: 'All model ids the active provider config exposes. Order matches
the admin''s comma-separated `configuration.model` value; the
first entry is the default.
'
example:
- gpt-4o-mini-tts
- tts-1
isDefault:
type: boolean
description: '`true` when the returned config was picked because it is
flagged `isDefault` in `aiModels`; `false` when no entry was
flagged and the server fell back to the first configured one.
'
example: true
modelKey:
type:
- string
- 'null'
description: 'Stable identifier assigned to the config entry by the admin
UI. Useful for tying the capability summary back to a specific
row under `/services/aiModels`.
'
friendlyName:
type:
- string
- 'null'
description: Optional display name configured by the admin.
example: Production TTS
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat: JWT
description: 'JWT Bearer token for authenticated requests.
A personal access token (see the **Personal Access Tokens** tag) is a
`phpat_`-prefixed variant of this same JWT — e.g. `phpat_eyJhbGci...`.
The prefix is display-only, added for secret-scanner detectability; the
gateway strips it before verifying the token, so send it exactly as
issued, prefix included.
'
scopedToken:
type: http
scheme: bearer
bearerFormat: JWT
description: 'Scoped JWT token for service-to-service authentication.
Format: "Bearer {scoped_token}"
Required scopes vary by endpoint.
'
oauth2:
type: oauth2
description: 'OAuth 2.0 authentication with fine-grained scopes.
Supports authorization_code (with PKCE) and client_credentials flows.
OAuth tokens are Bearer JWTs — use the same Authorization header as regular tokens.
For **client_credentials**, machine JWTs may use `userId === client_id`; the Node gateway resolves the OAuth app creator — see **OAuth Provider** tag.
'
flows:
authorizationCode:
authorizationUrl: /api/v1/oauth2/authorize
tokenUrl: /api/v1/oauth2/token
refreshUrl: /api/v1/oauth2/token
scopes:
openid: OpenID Connect authentication
profile: User profile information
email: User email address
offline_access: Offline access (refresh tokens)
org:read: Read organization information
org:write: Update organization settings
org:admin: Full organization administration
user:read: Read user profiles
user:write: Update user profiles
user:invite: Invite new users
user:delete: Delete users
usergroup:read: Read user groups
usergroup:write: Create and manage user groups
team:read: Read team information
team:write: Create and manage teams
kb:read: Read knowledge bases and records
kb:write: Create and update knowledge bases
kb:delete: Delete knowledge bases and records
kb:upload: Upload files to knowledge bases
semantic:read: Read semantic search results and history
semantic:write: Execute semantic search
semantic:delete: Delete semantic search history
conversation:read: Read conversations
conversation:write: Create and manage conversations
conversation:chat: Send messages in conversations
project:read: Read projects and their conversations
project:write: Create and manage projects
project:delete: Delete projects
agent:read: Read AI agents
agent:write: Create and manage AI agents
agent:execute: Execute AI agents
connector:read: Read connector configurations
connector:write: Create and update connectors
connector:sync: Trigger connector synchronization
connector:delete: Delete connectors
config:read: Read system configuration
config:write: Update system configuration
crawl:read: Read crawling jobs
crawl:write: Create and manage crawling jobs
crawl:delete: Delete crawling jobs
clientCredentials:
tokenUrl: /api/v1/oauth2/token
scopes:
openid: OpenID Connect authentication
profile: User profile information
email: User email address
offline_access: Offline access (refresh tokens)
org:read: Read organization information
org:write: Update organization settings
org:admin: Full organization administration
user:read: Read user profiles
user:write: Update user profiles
user:invite: Invite new users
user:delete: Delete users
usergroup:read: Read user groups
usergroup:write: Create and manage user groups
team:read: Read team information
team:write: Create and manage teams
kb:read: Read knowledge bases and records
kb:write: Create and update knowledge bases
kb:delete: Delete knowledge bases and records
kb:upload: Upload files to knowledge bases
semantic:write: Execute semantic search
semantic:read: Read semantic search results and history
semantic:delete: Delete semantic search history
conversation:read: Read conversations
conversation:write: Create and manage conversations
conversation:chat: Send messages in conversations
project:read: Read projects and their conversations
project:write: Create and manage projects
project:delete: Delete projects
agent:read: Read AI agents
agent:write: Create and manage AI agents
agent:execute: Execute AI agents
connector:read: Read connector configurations
connector:write: Create and update connectors
connector:sync: Trigger connector synchronization
connector:delete: Delete connectors
config:read: Read system configuration
config:write: Update system configuration
crawl:read: Read crawling jobs
crawl:write: Create and manage crawling jobs
x-refined-from:
- pipeshub-openapi.yaml
- pipeshub-openapi.yml