M13-SpeechServices (0.0.13)

New Issue

TTS and STT integration for Mosaic Stack. Tiered architecture: Kokoro (CPU default TTS), Chatterbox (GPU premium TTS with voice cloning), Speaches+faster-whisper (STT). All OpenAI-compatible API endpoints.

2026-05-17

100% Completed

0 Open 20 Closed

Label

Show archived labels Use alt + click/enter to exclude labels

All labels No label

ai

api

api

auth

database

database

devops

docs

frontend

graph

knowledge-module

migration

orchestrator

p0

p1

p2

p3

performance

phase-1

phase-2

phase-3

phase-4

phase-5

plugin

search

security

setup

testing

web

Project

All projects No project

Author

All users

Assignee

Assigned to nobody Assigned to anybody

jason.woltje

Sort

Newest Oldest Most recently updated Least recently updated Most commented Least commented Nearest due date Farthest due date

Label

feat: M13-SpeechServices — TTS & STT integration

#409 by jason.woltje was merged 2026-02-15 18:37:54 +00:00

develop

feature/m13-speech-services

0 / 7

Documentation: Speech services architecture, API, and deployment

#406 by jason.woltje was closed 2026-02-15 09:27:40 +00:00 0 / 5

1

E2E integration tests for speech services

#405 by jason.woltje was closed 2026-02-15 09:27:39 +00:00 0 / 8

1

Frontend speech settings page (provider selection, voice config)

#404 by jason.woltje was closed 2026-02-15 09:27:39 +00:00

1

Frontend audio playback component for TTS output

#403 by jason.woltje was closed 2026-02-15 09:27:39 +00:00

1

Frontend voice input component (microphone capture + transcription)

#402 by jason.woltje was closed 2026-02-15 09:27:38 +00:00 0 / 8

1

Speech services environment variables and ConfigModule integration

#401 by jason.woltje was closed 2026-02-15 09:27:38 +00:00 0 / 5

1

Docker Compose swarm/prod deployment for speech services

#400 by jason.woltje was closed 2026-02-15 09:27:37 +00:00 0 / 6

1

Docker Compose dev overlay for speech services

#399 by jason.woltje was closed 2026-02-15 09:27:37 +00:00 0 / 7

1

Audio format validation and preprocessing middleware

#398 by jason.woltje was closed 2026-02-15 09:27:36 +00:00 0 / 5

1

Implement WebSocket streaming transcription endpoint

#397 by jason.woltje was closed 2026-02-15 09:27:35 +00:00 0 / 7

1

Create /api/speech/synthesize REST endpoint

#396 by jason.woltje was closed 2026-02-15 09:27:34 +00:00 0 / 8

1

Implement Piper TTS provider via OpenedAI Speech (fallback tier)

#395 by jason.woltje was closed 2026-02-15 09:27:34 +00:00 0 / 4

1

Implement Chatterbox TTS provider (premium tier, voice cloning)

#394 by jason.woltje was closed 2026-02-15 09:27:33 +00:00 0 / 6

1

Implement Kokoro-FastAPI TTS provider (default tier)

#393 by jason.woltje was closed 2026-02-15 09:27:33 +00:00 0 / 6

1

Create /api/speech/transcribe REST endpoint

#392 by jason.woltje was closed 2026-02-15 09:27:32 +00:00 0 / 7

1

Implement tiered TTS provider architecture

#391 by jason.woltje was closed 2026-02-15 09:27:32 +00:00 0 / 6

1

Implement STT provider with Speaches/faster-whisper integration

#390 by jason.woltje was closed 2026-02-15 09:27:31 +00:00 0 / 6

1

Create SpeechModule with provider abstraction layer

#389 by jason.woltje was closed 2026-02-15 09:27:31 +00:00 0 / 6

1

EPIC: M13-SpeechServices — TTS & STT Integration

#388 by jason.woltje was closed 2026-02-15 09:30:23 +00:00

1