Skip to content

Commit 9911a79

Browse files
sfortissfortis
committed
v3.2
1 parent 2e8ebec commit 9911a79

File tree

16 files changed

+300
-212
lines changed

16 files changed

+300
-212
lines changed

‎README.md

Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -11,13 +11,16 @@ The OpenAI TTS component for Home Assistant makes it possible to use the OpenAI
1111
visit: (https://platform.openai.com/docs/pricing)
1212

1313

14-
## Features
14+
## Features
15+
16+
- 🗣️ **Text-to-Speech** conversion using OpenAI's API
17+
- 🌍 **Support for multiple languages and voices** No special configuration is needed. The AI model will auto-recognize the language.
18+
- ⭐🔔 **(New!) Chime option** – Useful for announcements on speakers. (See Devices --> OpenAI TTS --> CONNFIGURE button)
19+
- ⭐🔔 **(New!) User configurable chime sounds** – Drop your own chime sound into config/custom_components/openai_tts/chime folder (mp3).
20+
- ⭐🎛️ **(New!) Audio normalization option** – Uses more CPU but provides better audible sound on mobile phones and small speakers. (See Devices --> OpenAI TTS --> CONNFIGURE button)
21+
- 🎙️ **Customizable speech model** ([Check supported voices and models](https://platform.openai.com/docs/guides/text-to-speech))
22+
- 🏡 **Integration with Home Assistant** – Works with assistant, automations, and scripts.
1523

16-
- Text-to-Speech conversion using OpenAI's API
17-
- Support for multiple languages and voices
18-
- Chime option. Usefull for announcements.
19-
- Customizable speech model (check https://platform.openai.com/docs/guides/text-to-speech for supported voices and models)
20-
- Integration with Home Assistant's assistant, automations and scripts
2124

2225
## YouTube sample video (its not a tutorial!)
2326

‎custom_components/openai_tts/chime/signal1.mp3

5.51 KB
Binary file not shown.

‎custom_components/openai_tts/chime/signal2.mp3

8.54 KB
Binary file not shown.

‎custom_components/openai_tts/chime/signal3.mp3

8.1 KB
Binary file not shown.

‎custom_components/openai_tts/chime/signal4.mp3

7.54 KB
Binary file not shown.

‎custom_components/openai_tts/chime/threetone.mp3

8.34 KB
Binary file not shown.

‎custom_components/openai_tts/config_flow.py

Lines changed: 58 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,7 @@
33
"""
44
from __future__ import annotations
55
from typing import Any
6+
import os
67
import voluptuous as vol
78
import logging
89
from urllib.parse import urlparse
@@ -13,7 +14,20 @@
1314
from homeassistant.helpers.selector import selector
1415
from homeassistant.exceptions import HomeAssistantError
1516

16-
from .const import CONF_API_KEY, CONF_MODEL, CONF_VOICE, CONF_SPEED, CONF_URL, DOMAIN, MODELS, VOICES, UNIQUE_ID
17+
from .const import (
18+
CONF_API_KEY,
19+
CONF_MODEL,
20+
CONF_VOICE,
21+
CONF_SPEED,
22+
CONF_URL,
23+
DOMAIN,
24+
MODELS,
25+
VOICES,
26+
UNIQUE_ID,
27+
CONF_CHIME_ENABLE, # Use constant for chime enable toggle
28+
CONF_CHIME_SOUND,
29+
CONF_NORMALIZE_AUDIO,
30+
)
1731

1832
_LOGGER = logging.getLogger(__name__)
1933

@@ -26,6 +40,26 @@ async def validate_user_input(user_input: dict):
2640
if user_input.get(CONF_VOICE) is None:
2741
raise ValueError("Voice is required")
2842

43+
def get_chime_options() -> list[dict[str, str]]:
44+
"""
45+
Scans the "chime" folder (located in the same directory as this file)
46+
and returns a list of options for the dropdown selector.
47+
Each option is a dict with 'value' (the file name) and 'label' (the file name without extension).
48+
"""
49+
chime_folder = os.path.join(os.path.dirname(__file__), "chime")
50+
try:
51+
files = os.listdir(chime_folder)
52+
except Exception as err:
53+
_LOGGER.error("Error listing chime folder: %s", err)
54+
files = []
55+
options = []
56+
for file in files:
57+
if file.lower().endswith(".mp3"):
58+
label = os.path.splitext(file)[0].title() # e.g. "Signal1.mp3" -> "Signal1"
59+
options.append({"value": file, "label": label})
60+
options.sort(key=lambda x: x["label"])
61+
return options
62+
2963
class OpenAITTSConfigFlow(ConfigFlow, domain=DOMAIN):
3064
"""Handle a config flow for OpenAI TTS."""
3165
VERSION = 1
@@ -63,7 +97,6 @@ async def async_step_user(self, user_input: dict[str, Any] | None = None):
6397
if user_input is not None:
6498
try:
6599
await validate_user_input(user_input)
66-
# Generate a random unique id so multiple integrations can be added.
67100
entry_id = generate_entry_id()
68101
user_input[UNIQUE_ID] = entry_id
69102
await self.async_set_unique_id(entry_id)
@@ -99,11 +132,24 @@ class OpenAITTSOptionsFlow(OptionsFlow):
99132
async def async_step_init(self, user_input: dict | None = None):
100133
if user_input is not None:
101134
return self.async_create_entry(title="", data=user_input)
135+
# Retrieve chime options using the executor to avoid blocking the event loop.
136+
chime_options = await self.hass.async_add_executor_job(get_chime_options)
102137
options_schema = vol.Schema({
138+
# Use constant for chime enable toggle so the label comes from strings.json
103139
vol.Optional(
104-
"chime",
105-
default=self.config_entry.options.get("chime", self.config_entry.data.get("chime", False))
140+
CONF_CHIME_ENABLE,
141+
default=self.config_entry.options.get(CONF_CHIME_ENABLE, self.config_entry.data.get(CONF_CHIME_ENABLE, False))
106142
): selector({"boolean": {}}),
143+
144+
vol.Optional(
145+
CONF_CHIME_SOUND,
146+
default=self.config_entry.options.get(CONF_CHIME_SOUND, self.config_entry.data.get(CONF_CHIME_SOUND, "threetone.mp3"))
147+
): selector({
148+
"select": {
149+
"options": chime_options
150+
}
151+
}),
152+
107153
vol.Optional(
108154
CONF_SPEED,
109155
default=self.config_entry.options.get(CONF_SPEED, self.config_entry.data.get(CONF_SPEED, 1.0))
@@ -115,6 +161,7 @@ async def async_step_init(self, user_input: dict | None = None):
115161
"mode": "slider"
116162
}
117163
}),
164+
118165
vol.Optional(
119166
CONF_VOICE,
120167
default=self.config_entry.options.get(CONF_VOICE, self.config_entry.data.get(CONF_VOICE, "shimmer"))
@@ -125,6 +172,12 @@ async def async_step_init(self, user_input: dict | None = None):
125172
"sort": True,
126173
"custom_value": True
127174
}
128-
})
175+
}),
176+
177+
# Normalization toggle using its constant; label will be picked from strings.json.
178+
vol.Optional(
179+
CONF_NORMALIZE_AUDIO,
180+
default=self.config_entry.options.get(CONF_NORMALIZE_AUDIO, self.config_entry.data.get(CONF_NORMALIZE_AUDIO, False))
181+
): selector({"boolean": {}})
129182
})
130183
return self.async_show_form(step_id="init", data_schema=options_schema)

‎custom_components/openai_tts/const.py

Lines changed: 14 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,18 @@
1-
""" Constants for OpenAI TTS custom component"""
1+
"""
2+
Constants for OpenAI TTS custom component
3+
"""
24

35
DOMAIN = "openai_tts"
4-
CONF_API_KEY = 'api_key'
5-
CONF_MODEL = 'model'
6-
CONF_VOICE = 'voice'
7-
CONF_SPEED = 'speed'
8-
CONF_URL = 'url'
9-
UNIQUE_ID = 'unique_id'
6+
CONF_API_KEY = "api_key"
7+
CONF_MODEL = "model"
8+
CONF_VOICE = "voice"
9+
CONF_SPEED = "speed"
10+
CONF_URL = "url"
11+
UNIQUE_ID = "unique_id"
12+
1013
MODELS = ["tts-1", "tts-1-hd"]
1114
VOICES = ["alloy", "ash", "coral", "echo", "fable", "onyx", "nova", "sage", "shimmer"]
15+
16+
CONF_CHIME_ENABLE = "chime"
17+
CONF_CHIME_SOUND = "chime_sound"
18+
CONF_NORMALIZE_AUDIO = "normalize_audio"

‎custom_components/openai_tts/manifest.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -10,5 +10,5 @@
1010
"iot_class": "cloud_polling",
1111
"issue_tracker": "https://github.com/sfortis/openai_tts/issues",
1212
"requirements": [],
13-
"version": "0.3.1b0"
13+
"version": "0.3.2"
1414
}

‎custom_components/openai_tts/openaitts_engine.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ def __init__(self, api_key: str, voice: str, model: str, speed: float, url: str)
2626
self._url = url
2727

2828
def get_tts(self, text: str, speed: float = None, voice: str = None) -> AudioResponse:
29-
"""Synchronous TTS request using urllib.request
29+
"""Synchronous TTS request using urllib.request.
3030
If the API call fails, waits for 1 second and retries once.
3131
"""
3232
if speed is None:
@@ -42,7 +42,7 @@ def get_tts(self, text: str, speed: float = None, voice: str = None) -> AudioRes
4242
"model": self._model,
4343
"input": text,
4444
"voice": voice,
45-
"response_format": "wav",
45+
"response_format": "mp3",
4646
"speed": speed
4747
}
4848

‎custom_components/openai_tts/strings.json

Lines changed: 9 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -7,28 +7,26 @@
77
"data": {
88
"api_key": "Enter OpenAI API key",
99
"speed": "Speed (0.25 to 4.0, where 1.0 is default)",
10-
"model": "Select model",
11-
"voice": "Select voice",
12-
"url": "Enter the OpenAI-compatible endpoint. Optionally include a port number."
10+
"model": "Model",
11+
"voice": "Voice",
12+
"url": "Enter an OpenAI-compatible endpoint (optionally include a port number)."
1313
}
1414
}
1515
},
1616
"error": {
17-
"wrong_api_key": "Invalid API key. Please enter a valid API key.",
18-
"already_configured": "This voice and endpoint are already configured."
19-
},
20-
"abort": {
21-
"already_configured": "This voice and endpoint are already configured."
17+
"wrong_api_key": "Invalid API key. Please enter a valid API key."
2218
}
2319
},
2420
"options": {
2521
"step": {
2622
"init": {
2723
"title": "Configure TTS options",
2824
"data": {
29-
"chime": "Enable chime before speech (useful for announcements)",
30-
"speed": "Set speed (0.25 to 4.0)",
31-
"voice": "Select voice"
25+
"chime": "Enable chime sound prior speech (useful for announcements)",
26+
"chime_sound": "Chime sound",
27+
"speed": "Speed (0.25 to 4.0)",
28+
"voice": "Voice",
29+
"normalize_audio": "Enable loudness for generated audio (uses more CPU)"
3230
}
3331
}
3432
}

‎custom_components/openai_tts/translations/cs.json

Lines changed: 10 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -7,28 +7,26 @@
77
"data": {
88
"api_key": "Zadejte OpenAI API klíč",
99
"speed": "Rychlost (0,25 až 4,0, kde 1,0 je výchozí)",
10-
"model": "Vyberte model",
11-
"voice": "Vyberte hlas",
12-
"url": "Zadejte OpenAI-kompatibilní endpoint (Volitelně uveďte číslo portu)"
10+
"model": "Model",
11+
"voice": "Hlas",
12+
"url": "Zadejte endpoint kompatibilní s OpenAI (volitelně uveďte číslo portu)."
1313
}
1414
}
1515
},
1616
"error": {
17-
"wrong_api_key": "Neplatný API klíč. Zadejte prosím platný API klíč.",
18-
"already_configured": "Tento hlas a tento endpoint jsou již nakonfigurovány."
19-
},
20-
"abort": {
21-
"already_configured": "Tento hlas a tento endpoint jsou již nakonfigurovány."
17+
"wrong_api_key": "Neplatný API klíč. Zadejte prosím platný API klíč."
2218
}
2319
},
2420
"options": {
2521
"step": {
2622
"init": {
27-
"title": "Nastavení TTS možností",
23+
"title": "Nastavte TTS možnosti",
2824
"data": {
29-
"chime": "Povolit zvukový signál před řečí (užitečné pro oznámení)",
30-
"speed": "Nastavit rychlost (0,25 až 4,0)",
31-
"voice": "Vyberte hlas"
25+
"chime": "Povolte zvukový signál před řečí (užitečné pro oznámení)",
26+
"chime_sound": "Zvuk zvukového signálu",
27+
"speed": "Rychlost (0,25 až 4,0)",
28+
"voice": "Hlas",
29+
"normalize_audio": "Povolte zvýšení hlasitosti generovaného audia (vyžaduje více CPU)"
3230
}
3331
}
3432
}

‎custom_components/openai_tts/translations/de.json

Lines changed: 11 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -6,29 +6,27 @@
66
"description": "Weitere Informationen finden Sie in der Dokumentation.",
77
"data": {
88
"api_key": "Geben Sie den OpenAI API-Schlüssel ein",
9-
"speed": "Geschwindigkeit (0.25 bis 4.0, wobei 1.0 Standard ist)",
10-
"model": "Wählen Sie das Modell aus",
11-
"voice": "Wählen Sie die Stimme aus",
12-
"url": "Geben Sie den OpenAI-kompatiblen Endpunkt ein (Optional können Sie eine Portnummer angeben)"
9+
"speed": "Geschwindigkeit (0,25 bis 4,0, wobei 1,0 Standard ist)",
10+
"model": "Modell",
11+
"voice": "Stimme",
12+
"url": "Geben Sie einen OpenAI-kompatiblen Endpunkt ein (optional können Sie eine Portnummer angeben)."
1313
}
1414
}
1515
},
1616
"error": {
17-
"wrong_api_key": "Ungültiger API-Schlüssel. Bitte geben Sie einen gültigen API-Schlüssel ein.",
18-
"already_configured": "Diese Stimme und dieser Endpunkt sind bereits konfiguriert."
19-
},
20-
"abort": {
21-
"already_configured": "Diese Stimme und dieser Endpunkt sind bereits konfiguriert."
17+
"wrong_api_key": "Ungültiger API-Schlüssel. Bitte geben Sie einen gültigen API-Schlüssel ein."
2218
}
2319
},
2420
"options": {
2521
"step": {
2622
"init": {
27-
"title": "TTS-Optionen konfigurieren",
23+
"title": "Konfigurieren Sie die TTS-Optionen",
2824
"data": {
29-
"chime": "Chime vor der Sprache aktivieren (nützlich für Ansagen)",
30-
"speed": "Geschwindigkeit einstellen (0.25 bis 4.0)",
31-
"voice": "Stimme auswählen"
25+
"chime": "Aktivieren Sie den Signalton vor der Sprache (nützlich für Ansagen)",
26+
"chime_sound": "Signalton",
27+
"speed": "Geschwindigkeit (0,25 bis 4,0)",
28+
"voice": "Stimme",
29+
"normalize_audio": "Aktivieren Sie die Lautstärkeerhöhung für das erzeugte Audio (verwendet mehr CPU)"
3230
}
3331
}
3432
}

‎custom_components/openai_tts/translations/el.json

Lines changed: 11 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -3,32 +3,30 @@
33
"step": {
44
"user": {
55
"title": "Προσθήκη μετατροπής κειμένου σε ομιλία",
6-
"description": "Δείτε την τεκμηρίωση για περισσότερες πληροφορίες.",
6+
"description": "Δείτε την τεκμηρίωση για περαιτέρω πληροφορίες.",
77
"data": {
88
"api_key": "Εισάγετε το API key του OpenAI",
9-
"speed": "Ταχύτητα (0.25 έως 4.0, όπου το 1.0 είναι η προεπιλογή)",
10-
"model": "Επιλέξτε μοντέλο",
11-
"voice": "Επιλέξτε φωνή",
12-
"url": "Εισάγετε το custom API endpoint, συμβατό με OpenAI ( Προαιρετικά συμπεριλάβετε τον αριθμό της πόρτας)"
9+
"speed": "Ταχύτητα (0.25 έως 4.0, όπου το 1.0 είναι προεπιλογή)",
10+
"model": "Μοντέλο",
11+
"voice": "Φωνή",
12+
"url": "Εισάγετε ένα endpoint συμβατό με OpenAI (προαιρετικά συμπεριλάβετε αριθμό θύρας)."
1313
}
1414
}
1515
},
1616
"error": {
17-
"wrong_api_key": "Μη έγκυρο κλειδί API. Παρακαλώ εισάγετε ένα έγκυρο κλειδί API.",
18-
"already_configured": "Αυτή η φωνή και το σημείο τερματισμού είναι ήδη διαμορφωμένα."
19-
},
20-
"abort": {
21-
"already_configured": "Αυτή η φωνή και το σημείο τερματισμού είναι ήδη διαμορφωμένα."
17+
"wrong_api_key": "Μη έγκυρο API key. Εισάγετε ένα έγκυρο API key."
2218
}
2319
},
2420
"options": {
2521
"step": {
2622
"init": {
2723
"title": "Διαμορφώστε τις επιλογές TTS",
2824
"data": {
29-
"chime": "Ενεργοποιήστε το ηχητικό σήμα πριν από την ομιλία (χρήσιμο για ανακοινώσεις)",
30-
"speed": "Ρυθμίστε την ταχύτητα (0.25 έως 4.0)",
31-
"voice": "Επιλέξτε φωνή"
25+
"chime": "Ενεργοποιήστε τον ήχο του ηχητικού σήματος πριν από την ομιλία (χρήσιμο για ανακοινώσεις)",
26+
"chime_sound": "Ήχος ηχητικού σήματος",
27+
"speed": "Ταχύτητα (0.25 έως 4.0)",
28+
"voice": "Φωνή",
29+
"normalize_audio": "Ενεργοποιήστε την αύξηση της έντασης για τον παραγόμενο ήχο (χρησιμοποιεί περισσότερη CPU)"
3230
}
3331
}
3432
}

‎custom_components/openai_tts/translations/en.json

Lines changed: 9 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -7,28 +7,26 @@
77
"data": {
88
"api_key": "Enter OpenAI API key",
99
"speed": "Speed (0.25 to 4.0, where 1.0 is default)",
10-
"model": "Select model",
11-
"voice": "Select voice",
12-
"url": "Enter the OpenAI-compatible endpoint. Optionally include a port number."
10+
"model": "Model",
11+
"voice": "Voice",
12+
"url": "Enter an OpenAI-compatible endpoint (optionally include a port number)."
1313
}
1414
}
1515
},
1616
"error": {
17-
"wrong_api_key": "Invalid API key. Please enter a valid API key.",
18-
"already_configured": "This voice and endpoint are already configured."
19-
},
20-
"abort": {
21-
"already_configured": "This voice and endpoint are already configured."
17+
"wrong_api_key": "Invalid API key. Please enter a valid API key."
2218
}
2319
},
2420
"options": {
2521
"step": {
2622
"init": {
2723
"title": "Configure TTS options",
2824
"data": {
29-
"chime": "Enable chime before speech (useful for announcements)",
30-
"speed": "Set speed (0.25 to 4.0)",
31-
"voice": "Select voice"
25+
"chime": "Enable chime sound prior speech (useful for announcements)",
26+
"chime_sound": "Chime sound",
27+
"speed": "Speed (0.25 to 4.0)",
28+
"voice": "Voice",
29+
"normalize_audio": "Enable loudness for generated audio (uses more CPU)"
3230
}
3331
}
3432
}

0 commit comments

Comments
 (0)