Implement STT provider with Speaches/faster-whisper integration #390

Closed
opened 2026-02-15 07:33:20 +00:00 by jason.woltje · 1 comment
Owner

Description

Implement that connects to a Speaches server (faster-whisper backend) via the OpenAI-compatible endpoint.

Implementation

Provider

Environment Variables

Acceptance Criteria

  • SpeachesSttProvider implements ISTTProvider
  • Connects via OpenAI SDK with configurable base URL
  • Supports model selection via config
  • Supports language parameter
  • Handles connection errors gracefully
  • Unit tests with mocked OpenAI client
## Description Implement that connects to a Speaches server (faster-whisper backend) via the OpenAI-compatible endpoint. ## Implementation ### Provider ### Environment Variables ## Acceptance Criteria - [ ] SpeachesSttProvider implements ISTTProvider - [ ] Connects via OpenAI SDK with configurable base URL - [ ] Supports model selection via config - [ ] Supports language parameter - [ ] Handles connection errors gracefully - [ ] Unit tests with mocked OpenAI client
jason.woltje added this to the M13-SpeechServices (0.0.13) milestone 2026-02-15 07:33:20 +00:00
Author
Owner

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-STT-001: STT provider with Speaches/faster-whisper integration (commit 3ae9e53, 27 tests). All quality gates passed (lint, typecheck, tests, security).

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-STT-001: STT provider with Speaches/faster-whisper integration (commit 3ae9e53, 27 tests). All quality gates passed (lint, typecheck, tests, security).
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: mosaic/stack#390