Home Assistant text to speech: the OpenAI TTS integration with a custom endpoint
The OpenAI TTS custom integration has a preset for any OpenAI-compatible endpoint. Put ours in and your announcements and voice assistant replies get natural voices, with no local TTS server.
1. Get a key
Get an access key on the pricing page: $1 once (1,000 credits) or $3 a month (3,000 credits, about 60 hours). After paying you get a page that shows the key (it starts with adt_). That key is the API key in every app below.
2. Install the integration
- In HACS, search for OpenAI TTS (sfortis/openai_tts) and install it, then restart Home Assistant.
- Settings → Devices & services → Add integration → OpenAI TTS.
- Choose the preset Custom / Self-hosted (any OpenAI-compatible endpoint).
- Fill in:
| URL | https://glyphcall.com/v1/audio/speech |
|---|---|
| API key | adt_… (your key) |
| Model | tts-1 |
| Voice | nova |
| Speed | 1.0 |
| Audio format | mp3 |
The URL is the full /v1/audio/speech path. Keep speed at 1.0 and the format at mp3: other values are refused, uncharged. The integration may look for a voice list first; if it asks you to type a voice, use an OpenAI name or one from the voice list.
3. Try it
action: tts.speak
target:
entity_id: tts.openai_tts
data:
media_player_entity_id: media_player.living_room
message: "The washing machine has finished."
Your entity ids may differ: check Developer tools → States. A short announcement is one $0.01 call.
Test the key first
If something does not work in the app, check the key and the endpoint with one call from a terminal:
curl https://glyphcall.com/v1/audio/speech \
-H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" \
-d '{"model":"tts-1","input":"Hello from Glyphcall Voice.","voice":"nova"}' -o hello.mp3
What it costs
| Call | Price |
|---|---|
| Text to speech, up to 300 characters | $0.01 (10 credits) |
| Text to speech, 301 to 2,000 characters | $0.08 (80 credits) |
| Speech to text, a file up to 5 MB | $0.01 (10 credits) |
| Speech to text, a larger MP3 or WAV up to 60 minutes / 25 MB | $0.05 (50 credits) |
A failed call is never charged. No account, no subscription unless you choose the monthly plan.
Questions
Does this replace Piper? It is an alternative when you want more natural voices and do not want to run a model on your Home Assistant host.
Can it do Spanish? Yes, with the Spanish voice names on the voice list, if the integration lets you send language es as an extra parameter. Otherwise English voices only.
Other guides: Open WebUI · LibreChat · AnythingLLM · Obsidian Whisper · Any other app · OpenAI tts-1 shutdown · OpenAI whisper-1 shutdown · Voice list