Skip to content

Refactor voice data handling and logging #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
rabbidiesel wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Refactor voice data handling and logging #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9be2aa9
Refactor voice data handling and logging
rabbidiesel Jan 7, 2026
787e248
Merge branch 'main' into main
markjcrane Jan 7, 2026
56bf2e5
Update default_setting_description for Text to Speech
rabbidiesel Jan 21, 2026
6de47f5
Refactor get_voices to return structured voice data
rabbidiesel Jan 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion app_config.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@
$apps[$x]['default_settings'][$y]['default_setting_name'] = "text";
$apps[$x]['default_settings'][$y]['default_setting_value'] = "openai";
$apps[$x]['default_settings'][$y]['default_setting_enabled'] = "false";
$apps[$x]['default_settings'][$y]['default_setting_description'] = "Text to Speech API engine.";
$apps[$x]['default_settings'][$y]['default_setting_description'] = "Text to Speech API engine. openai, elevenlabs, inworld";
$y++;
$apps[$x]['default_settings'][$y]['default_setting_uuid'] = "eced068b-db30-4257-aa7c-6e2659271e4b";
$apps[$x]['default_settings'][$y]['default_setting_category'] = "speech";
Expand Down
64 changes: 23 additions & 41 deletions resources/classes/speech_inworld.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,13 +63,13 @@ public function __construct($settings = null) {
//assign private variables
$this->app_name = 'speech';
$this->app_uuid = 'f9a4f42e-2e31-4c24-8da2-0d0349611e3f';

//set defaults
$this->domain = 'api.inworld.ai'; // Inworld API domain

//store settings object
$this->settings = $settings;

//get API key from settings if available
//FusionPBX uses a generic 'api_key' setting that's shared across all speech providers
if ($settings !== null) {
Expand Down Expand Up @@ -142,13 +142,13 @@ public function get_languages() : array {
public function get_voices() : array {
// Initialize voices array
$voices = [];

// Only try API if we have an api_key set
if (!empty($this->api_key)) {
try {
// Inworld API endpoint for listing voices
$url = "https://api.inworld.ai/tts/v1/voices";

$headers = [
'Authorization: Basic ' . $this->api_key,
'Accept: application/json'
Expand All @@ -166,57 +166,44 @@ public function get_voices() : array {
$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
$curl_error = curl_error($ch);
unset($ch);
curl_close($ch);

// Parse successful response
if ($http_code == 200 && $response) {
$json_response = json_decode($response, true);

// Inworld returns: {"voices": [{"voiceId": "...", "displayName": "...", ...}]}
if (isset($json_response['voices']) && is_array($json_response['voices'])) {
foreach ($json_response['voices'] as $voice) {
$voice_id = $voice['voiceId'] ?? $voice['name'] ?? '';
$display_name = $voice['displayName'] ?? $voice['name'] ?? $voice_id;
$description = $voice['description'] ?? '';
$languages = $voice['languages'] ?? [];

// If displayName is empty, use voiceId
if (empty($display_name)) {
$display_name = $voice_id;
}

if (!empty($voice_id)) {
// Build detailed voice info
$voice_info = $display_name;

// Add description if available
if (!empty($description)) {
$voice_info .= ' - ' . $description;
}

// Add language if available
if (!empty($languages) && is_array($languages)) {
$language_codes = implode(', ', $languages);
$voice_info .= ' (' . $language_codes . ')';
}

$voices[$voice_id] = $voice_info;
// Store structured voice data for JavaScript access
$voices[$voice_id] = [
'name' => $display_name,
'description' => $description,
'languages' => $languages
];
}
}

error_log("Inworld API: Successfully fetched " . count($voices) . " voices");

}
} else {
error_log("Inworld API Error: HTTP $http_code" . ($curl_error ? " - $curl_error" : ""));
if ($response) {
error_log("Response: " . substr($response, 0, 500));
}
}
} catch (Exception $e) {
error_log("Inworld API Exception: " . $e->getMessage());
}
}

// If no voices were fetched, return empty array (like ElevenLabs does)
// This way the dropdown will be empty if API key is invalid/missing
return $voices;
Expand Down Expand Up @@ -245,7 +232,7 @@ public function download() {
//prepare the API request
// Inworld TTS synthesize endpoint (non-streaming)
$url = "https://api.inworld.ai/tts/v1/voice";

$headers = [
'Content-Type: application/json',
'Authorization: Basic ' . $this->api_key
Expand Down Expand Up @@ -278,7 +265,7 @@ public function download() {
$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
$curl_error = curl_error($ch);
unset($ch);
curl_close($ch);

//debug output
if ($this->debug) {
Expand All @@ -292,26 +279,23 @@ public function download() {
if ($http_code == 200 && $response) {
// Inworld returns JSON with base64 audio in 'audioContent' field
$json_response = json_decode($response, true);

// Debug: log what we got
error_log("Inworld API response keys: " . ($json_response ? implode(', ', array_keys($json_response)) : 'NOT JSON'));


if (isset($json_response['audioContent'])) {
// Decode base64 audio data
$audio_data = base64_decode($json_response['audioContent']);

// Save to file
if (file_put_contents($this->file, $audio_data)) {
if ($this->debug) {
echo "Audio saved successfully to: " . $this->file . "\n";
}
error_log("Inworld: Audio saved successfully to " . $this->file);
return true;
} else {
throw new Exception("Failed to write audio file to: " . $this->file);
}
} else {
error_log("Inworld API response (first 500 chars): " . substr($response, 0, 500));
throw new Exception("No audioContent in response. Keys found: " . ($json_response ? implode(', ', array_keys($json_response)) : 'NOT JSON'));
}
} else {
Expand All @@ -334,7 +318,7 @@ public function download() {
/**
* speech_interface implementation methods
*/

/**
* set_path - set the file path
*/
Expand Down Expand Up @@ -384,11 +368,9 @@ public function set_message(string $message) : void {
*/
public function speech() : bool {
try {
error_log("Inworld speech() called - voice: {$this->voice_id}, text: " . substr($this->text, 0, 50));
$this->download();
return true;
} catch (Exception $e) {
error_log("Inworld speech generation error: " . $e->getMessage());
return false;
}
}
Expand Down