REST with Client auth

Convert speech to text using client-side authentication

Convert audio to text with client-side JWT authentication. This endpoint is identical to the standard /api endpoint but uses a client token (JWT) instead of an org-level API key.

Request Body

audio · string · required

Base64 encoded, 16kHz wav audio. Maximum size is 25MB or 6 minutes of audio.

language · array

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).

context · object

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.

Show child attributes

app · object

Information about the application the user is dictating into, used to customize the writing style.

Show child attributes

name · string

The name of the application.

type · string

The type of the application. Currently supports the following list:

• email: Email clients and anywhere the user would be trying to dictate an email.
• ai: Applications where the user is conversing with an AI chatbot / agent and not a human.
• other: Any application that does not fit in the two groups above.

dictionary_context · array · default: "[]"

List of uncommon names or words relevant to the context that might be mentioned by the user.

user_identifier · string

User ID in the app that the person is dictating in, like their email address in an email client application.

user_first_name · string

First name of the speaker, used to make sure Flow spells the speaker’s name correctly.

user_last_name · string

Last name of the speaker.

textbox_contents · object

Text under and surrounding the cursor in the active textbox. Flow uses this information to decide casing, spacing and punctuation.

Show child attributes

before_text · object

The text immediately before the cursor.

selected_text · object

The text the user has highlighted.

after_text · object

The text immediately after the cursor.

screenshot · string

Screenshot of the screen or the app the user is dictating in, for when the user is referencing something on the screen.

content_text · string

Plaintext content of the current page in the app user is dictating in. This is a more efficient way of providing context compared to screenshot.

content_html · string

HTML content of the app user is dictating in (a more feature-rich alternative to content_text).

conversation · object

Chatbot style history of the conversation the user is dictating in. This typically applies to messaging and AI apps.

Show child attributes

id · string · required

Identifier of the conversation. For example name of group chat in case of a messaging app.

participants · array

List of names of other people in the conversation, used to get their names correct in case of uncommonly spelled names.

messages · array

List of recent messages in the conversation, in the chronological order. Used to identify proper context and names of things being mentioned that are not conversation participants.

Show message item attributes

role · string · required

Type of the message sender. One of: user, human, assistant

content · string · required

Content of the message.

properties · object · deprecated

Show properties

language · string · default: "en"

2-digit ISO language code (e.g. ‘en’, ‘es’)

app_type · string · default: "other"

Flow formats appropriately depending on if the user is prompting AI, writing an email, or other tasks. Options: ‘ai’, ‘email’, ‘other’

dictionary · array · default: "[]"

List of dictionary words to help with transcription accuracy

after_text · string · default: true

The text immediately after the cursor. Flow uses it to decide spacing / punctuation.

before_text · string · default: true

The text immediately before the cursor. Flow uses it to decide spacing / punctuation.

selected_text · string · default: true

The text the user has highlighted. Flow uses it to decide spacing / punctuation.

Response (200 OK)

{
  "id": "550e8400-e29b-41d4-a716-446655440000",
  "text": "Testing testing 1, 2, 3",
  "detected_language": "en",
  "total_time": 432,
  "generated_tokens": 9
}

Request

{
  "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
  }
}

Authorizations

Authorization · string · header · required

Client-side token (format: Bearer <JWT>) for calling client endpoints like /client_api.

Body

application/json

audio · string · required

Base64-encoded audio data (up to 25MB / 6 minutes)

properties · object · required

Additional config for transcription

Response

200

application/json

Successful transcription

id · string<uuid>

text · string

detected_language · string

total_time · number

generated_tokens · integer