Docker Compose dev overlay for speech services #399

Closed
opened 2026-02-15 07:34:59 +00:00 by jason.woltje · 1 comment
Owner

Description

Create Docker Compose overlay for local development with all speech services.

Services

docker-compose.speech.yml (dev overlay)

  • speaches: ghcr.io/speaches-ai/speaches:latest on port 8090:8000, volume speaches-models:/root/.cache/huggingface, env WHISPER__MODEL=Systran/faster-whisper-large-v3-turbo
  • kokoro-tts: ghcr.io/remsky/kokoro-fastapi:latest-cpu on port 8880:8880
  • chatterbox-tts (optional, premium-tts profile): devnen/chatterbox-tts-server:latest on port 8881:8000, requires GPU capability reservation

Usage

  • Basic (STT + default TTS): docker compose -f docker-compose.yml -f docker-compose.speech.yml up
  • With premium TTS: docker compose -f docker-compose.yml -f docker-compose.speech.yml --profile premium-tts up

Acceptance Criteria

  • docker-compose.speech.yml created
  • Speaches service configured
  • Kokoro-FastAPI service configured
  • Chatterbox behind optional profile
  • Networks connect to main compose internal network
  • Volume for model caching
  • Makefile targets: speech-up, speech-down, speech-logs
## Description Create Docker Compose overlay for local development with all speech services. ## Services ### docker-compose.speech.yml (dev overlay) - speaches: ghcr.io/speaches-ai/speaches:latest on port 8090:8000, volume speaches-models:/root/.cache/huggingface, env WHISPER__MODEL=Systran/faster-whisper-large-v3-turbo - kokoro-tts: ghcr.io/remsky/kokoro-fastapi:latest-cpu on port 8880:8880 - chatterbox-tts (optional, premium-tts profile): devnen/chatterbox-tts-server:latest on port 8881:8000, requires GPU capability reservation ### Usage - Basic (STT + default TTS): docker compose -f docker-compose.yml -f docker-compose.speech.yml up - With premium TTS: docker compose -f docker-compose.yml -f docker-compose.speech.yml --profile premium-tts up ## Acceptance Criteria - [ ] docker-compose.speech.yml created - [ ] Speaches service configured - [ ] Kokoro-FastAPI service configured - [ ] Chatterbox behind optional profile - [ ] Networks connect to main compose internal network - [ ] Volume for model caching - [ ] Makefile targets: speech-up, speech-down, speech-logs
jason.woltje added this to the M13-SpeechServices (0.0.13) milestone 2026-02-15 07:34:59 +00:00
Author
Owner

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-DOC-001: Docker Compose dev overlay for speech services (commit 52553c8). All quality gates passed (lint, typecheck, tests, security).

Completed as part of M13-SpeechServices milestone on branch feature/m13-speech-services. SP-DOC-001: Docker Compose dev overlay for speech services (commit 52553c8). 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#399