> ## Documentation Index
> Fetch the complete documentation index at: https://api-docs.wisprflow.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# REST with API key auth
> Convert speech to text using the REST API
Convert audio to text with support for multiple languages and context awareness. Use your API key for authentication.
### Request Body
Base64 encoded, 16kHz wav audio. Maximum size is 25MB or 6 minutes of audio.
Optional list of (ISO 639-1) language codes that the user is expected to speak.
Setting the list size to 1 forces the transcription into the specified language. Not providing an input attempts autodetection on full list of languages (less accurate).
Optional contextual information about the circumstances surrounding the user dictation.
Flow can use these information to make its output more accurate by for example, getting names right, resolving speech ambiguities, etc.
All properties are optional and will use default values if not provided.
See [Request Schema](/request_schema) page for an exhaustive list of context attributes.
Legacy API schema for providing context. Use the equivalent fields in the `context` field instead. If both `context` and `properties` are provided, `properties` will be ignored.
See [Request Schema](/request_schema) page for an exhaustive list of properties.
```json Response (200 OK) theme={null}
{
"id": "550e8400-e29b-41d4-a716-446655440000",
"text": "Testing testing 1, 2, 3",
"detected_language": "en",
"total_time": 432,
"generated_tokens": 9
}
```
```json Request theme={null}
{
"audio": "UklGRiQA....",
"language": ["en"],
"context": {
"app": {
"type": "email"
},
"dictionary_context": [],
"textbox_contents": {
"before_text": "",
"selected_text": "",
"after_text": ""
},
// ... for a full list of available fields, see the "Request Schema" page
}
}
```
## OpenAPI
````yaml POST /api
openapi: 3.1.0
info:
title: Flow Voice API
description: Speech-to-text API with advanced context awareness and language detection
version: 1.0.0
servers:
- url: https://platform-api.wisprflow.ai/api/v1/dash
description: Production server
security: []
paths:
/api:
post:
summary: Convert speech to text
description: >-
Transcribe audio with support for multiple languages and context
awareness
operationId: transcribeAudio
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- audio
- properties
properties:
audio:
type: string
description: >-
base64 encoded, 16kHz wav audio. Max size is 25MB / 6
minutes of audio
example: UklGRiQA....
properties:
type: object
description: Additional configuration properties for the transcription
properties:
language:
type: string
description: 2-digit ISO language code
example: en
default: en
app_type:
type: string
enum:
- ai
- email
- other
description: >-
Flow formats appropriately depending on if the user is
prompting AI, writing an email, or other tasks.
default: other
dictionary:
type: array
items:
type: string
description: >-
List of dictionary words to help with transcription
accuracy
default: []
after_text:
type: string
description: >-
The text immediately after the cursor. Flow uses it to
decide spacing / punctuation.
default: ''
before_text:
type: string
description: >-
The text immediately before the cursor. Flow uses it to
decide spacing / punctuation.
default: ''
selected_text:
type: string
description: >-
The text the user has highlighted. Flow uses it to
decide spacing / punctuation.
default: ''
responses:
'200':
description: Successful transcription
content:
application/json:
schema:
type: object
properties:
id:
type: string
format: uuid
description: Unique identifier for the transcription
example: 550e8400-e29b-41d4-a716-446655440000
text:
type: string
description: The transcribed text with formatting
example: Testing testing 1, 2, 3
detected_language:
type: string
description: Detected language code
example: en
total_time:
type: integer
description: Total processing time in milliseconds
example: 432
generated_tokens:
type: integer
description: Number of tokens used
example: 9
'400':
description: Bad request
content:
application/json:
schema:
type: object
properties:
detail:
type: string
example: No audio data provided!
'401':
description: Unauthorized
'413':
description: Payload too large
content:
application/json:
schema:
type: object
properties:
detail:
type: string
example: Audio file size exceeds 25MB limit
'500':
description: Internal server error
content:
application/json:
schema:
type: object
properties:
detail:
type: string
example: Error running inference
security:
- bearerAuth: []
components:
securitySchemes:
bearerAuth:
type: http
scheme: bearer
bearerFormat:
````