Skip to content

feat(voice): [ACL-2127] Add a sequence diagram to illustrate the Voice API flow #147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sj-dl merged 1 commit into from
Nov 14, 2025
Merged

feat(voice): [ACL-2127] Add a sequence diagram to illustrate the Voice API flow #147

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 43 additions & 0 deletions api-reference/voice.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,49 @@ Use the received URL to establish a WebSocket connection for:

See the [WebSocket Streaming](/api-reference/voice/websocket-streaming) documentation for details.

### Message Flow

```mermaid
sequenceDiagram
participant Client
participant Voice API

Note over Client,Voice API: Step 1: Request Session (POST)

Client->>Voice API: Configuration options
Voice API->>Client: Streaming URL

Note over Client,Voice API: Step 2: Start Streaming (WebSocket)

Client->>Voice API: Establish WebSocket connection<br>using the streaming URL

Note over Client,Voice API: WebSocket

par
loop Send audio data
Client->>Voice API: SourceMediaChunk
end
and
loop Receive updates
Voice API-->>Client: SourceTranscriptUpdate
Voice API-->>Client: TargetTranscriptUpdate
end
end

Client->>Voice API: EndOfSourceAudio

loop Final updates
Voice API-->>Client: SourceTranscriptUpdate
Voice API-->>Client: TargetTranscriptUpdate
end

Voice API-->>Client: EndOfSourceTranscript

Voice API-->>Client: EndOfTargetTranscript<br>(once per target language)

Note over Client,Voice API: Connection Closed
```

## Limitations and Constraints

* Maximum 5 target languages per stream
Expand Down