A Home Assistant custom integration for Amazon Polly TTS that supports the modern tts.speak service.
- ✅ Modern
tts.speakservice support (not just legacytts.xxx_say) - ✅ Config flow setup via UI (no YAML needed)
- ✅ All Amazon Polly voices supported
- ✅ Neural, Standard, Generative, and Long-form engines
- ✅ Multiple output formats (MP3, OGG, PCM)
- ✅ Configurable sample rates
- Open HACS in Home Assistant
- Click on "Integrations"
- Click the three dots in the top right corner
- Select "Custom repositories"
- Add
https://github.com/joopdo/polly_ttswith category "Integration" - Click "Install"
- Restart Home Assistant
- Download the
polly_ttsfolder from this repository - Copy it to
config/custom_components/polly_tts - Restart Home Assistant
- Go to Settings → Devices & Services
- Click + Add Integration
- Search for "Polly TTS"
- Enter your AWS credentials:
- AWS Access Key ID
- AWS Secret Access Key
- AWS Region (e.g.,
eu-west-1)
- Select your preferred voice and settings
- Create an AWS account at aws.amazon.com
- Go to IAM and create a new user with programmatic access
- Attach the
AmazonPollyReadOnlyAccesspolicy - Save the Access Key ID and Secret Access Key
action: tts.speak
target:
entity_id: tts.polly_lotte
data:
media_player_entity_id: media_player.living_room_speaker
message: "Hello, this is a test!"
## Credits
Original Amazon Polly integration by @jschlyter
Modern TTS Entity implementation by @joopdo
Largely vibe-coded with Claude Opus 4 🤖