pleb
1003 lines
28 KiB
JSON
1003 lines
28 KiB
JSON
{
|
|
"openapi": "3.1.0",
|
|
"info": {
|
|
"title": "Kokoro TTS API",
|
|
"description": "API for text-to-speech generation using Kokoro",
|
|
"version": "0.6.0-rc1"
|
|
},
|
|
"paths": {
|
|
"/v1/audio/speech": {
|
|
"post": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "Create Speech",
|
|
"description": "OpenAI-compatible endpoint for text-to-speech",
|
|
"operationId": "create_speech_v1_audio_speech_post",
|
|
"parameters": [
|
|
{
|
|
"name": "x-raw-response",
|
|
"in": "header",
|
|
"required": false,
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "X-Raw-Response"
|
|
}
|
|
}
|
|
],
|
|
"requestBody": {
|
|
"required": true,
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/OpenAISpeechRequest"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/download/{filename}": {
|
|
"get": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "Download Audio File",
|
|
"description": "Download a generated audio file from temp storage",
|
|
"operationId": "download_audio_file_v1_download__filename__get",
|
|
"parameters": [
|
|
{
|
|
"name": "filename",
|
|
"in": "path",
|
|
"required": true,
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Filename"
|
|
}
|
|
}
|
|
],
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/models": {
|
|
"get": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "List Models",
|
|
"description": "List all available models",
|
|
"operationId": "list_models_v1_models_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/models/{model}": {
|
|
"get": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "Retrieve Model",
|
|
"description": "Retrieve a specific model",
|
|
"operationId": "retrieve_model_v1_models__model__get",
|
|
"parameters": [
|
|
{
|
|
"name": "model",
|
|
"in": "path",
|
|
"required": true,
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Model"
|
|
}
|
|
}
|
|
],
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/audio/voices": {
|
|
"get": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "List Voices",
|
|
"description": "List all available voices for text-to-speech.\n\nReturns `[{\"id\": ..., \"name\": ...}, ...]` by default so OpenAI-compatible\nclients (Open WebUI in particular, which does `voice['id']` directly and\nsilently falls back to a hardcoded 6-voice list otherwise) can render the\nfull voice list. Pass `?legacy=true` for the pre-0.3.x plain-string shape.",
|
|
"operationId": "list_voices_v1_audio_voices_get",
|
|
"parameters": [
|
|
{
|
|
"name": "legacy",
|
|
"in": "query",
|
|
"required": false,
|
|
"schema": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"title": "Legacy"
|
|
}
|
|
}
|
|
],
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/audio/voices/combine": {
|
|
"post": {
|
|
"tags": [
|
|
"OpenAI Compatible TTS"
|
|
],
|
|
"summary": "Combine Voices",
|
|
"description": "Combine multiple voices into a new voice and return the .pt file.\n\nArgs:\n request: Either a string with voices separated by + (e.g. \"voice1+voice2\")\n or a list of voice names to combine\n\nReturns:\n FileResponse with the combined voice .pt file\n\nRaises:\n HTTPException:\n - 400: Invalid request (wrong number of voices, voice not found)\n - 500: Server error (file system issues, combination failed)",
|
|
"operationId": "combine_voices_v1_audio_voices_combine_post",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"type": "array"
|
|
}
|
|
],
|
|
"title": "Request"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/dev/phonemize": {
|
|
"post": {
|
|
"tags": [
|
|
"text processing"
|
|
],
|
|
"summary": "Phonemize Text",
|
|
"description": "Convert text to phonemes using Kokoro's quiet mode.\n\nArgs:\n request: Request containing text and language\n\nReturns:\n Phonemes and token IDs",
|
|
"operationId": "phonemize_text_dev_phonemize_post",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/PhonemeRequest"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/PhonemeResponse"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/dev/generate_from_phonemes": {
|
|
"post": {
|
|
"tags": [
|
|
"text processing"
|
|
],
|
|
"summary": "Generate From Phonemes",
|
|
"description": "Generate audio directly from phonemes using Kokoro's phoneme format",
|
|
"operationId": "generate_from_phonemes_dev_generate_from_phonemes_post",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/GenerateFromPhonemesRequest"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/dev/captioned_speech": {
|
|
"post": {
|
|
"tags": [
|
|
"text processing"
|
|
],
|
|
"summary": "Create Captioned Speech",
|
|
"description": "Generate audio with word-level timestamps using streaming approach",
|
|
"operationId": "create_captioned_speech_dev_captioned_speech_post",
|
|
"parameters": [
|
|
{
|
|
"name": "x-raw-response",
|
|
"in": "header",
|
|
"required": false,
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "X-Raw-Response"
|
|
}
|
|
}
|
|
],
|
|
"requestBody": {
|
|
"required": true,
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/CaptionedSpeechRequest"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/dev/unload": {
|
|
"post": {
|
|
"tags": [
|
|
"text processing"
|
|
],
|
|
"summary": "Unload Model",
|
|
"description": "Release the model from GPU VRAM without stopping the container.\n\nThe model reloads automatically on the next inference request.\nUseful for homelab deployments where GPU memory is shared across services.",
|
|
"operationId": "unload_model_dev_unload_post",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/debug/threads": {
|
|
"get": {
|
|
"tags": [
|
|
"debug"
|
|
],
|
|
"summary": "Get Thread Info",
|
|
"operationId": "get_thread_info_debug_threads_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/debug/storage": {
|
|
"get": {
|
|
"tags": [
|
|
"debug"
|
|
],
|
|
"summary": "Get Storage Info",
|
|
"operationId": "get_storage_info_debug_storage_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/debug/system": {
|
|
"get": {
|
|
"tags": [
|
|
"debug"
|
|
],
|
|
"summary": "Get System Info",
|
|
"operationId": "get_system_info_debug_system_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/debug/session_pools": {
|
|
"get": {
|
|
"tags": [
|
|
"debug"
|
|
],
|
|
"summary": "Get Session Pool Info",
|
|
"description": "Get information about ONNX session pools.",
|
|
"operationId": "get_session_pool_info_debug_session_pools_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/web/config": {
|
|
"get": {
|
|
"tags": [
|
|
"Web Player"
|
|
],
|
|
"summary": "Get Web Config",
|
|
"description": "Get web player configuration including UVICORN_ROOT_PATH.",
|
|
"operationId": "get_web_config_web_config_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/web/{filename}": {
|
|
"get": {
|
|
"tags": [
|
|
"Web Player"
|
|
],
|
|
"summary": "Serve Web File",
|
|
"description": "Serve web player static files asynchronously.",
|
|
"operationId": "serve_web_file_web__filename__get",
|
|
"parameters": [
|
|
{
|
|
"name": "filename",
|
|
"in": "path",
|
|
"required": true,
|
|
"schema": {
|
|
"type": "string",
|
|
"title": "Filename"
|
|
}
|
|
}
|
|
],
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
},
|
|
"404": {
|
|
"description": "Not found"
|
|
},
|
|
"422": {
|
|
"description": "Validation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/HTTPValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/health": {
|
|
"get": {
|
|
"summary": "Health Check",
|
|
"description": "Health check endpoint",
|
|
"operationId": "health_check_health_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/v1/test": {
|
|
"get": {
|
|
"summary": "Test Endpoint",
|
|
"description": "Test endpoint to verify routing",
|
|
"operationId": "test_endpoint_v1_test_get",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Successful Response",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"components": {
|
|
"schemas": {
|
|
"CaptionedSpeechRequest": {
|
|
"properties": {
|
|
"model": {
|
|
"type": "string",
|
|
"title": "Model",
|
|
"description": "The model to use for generation. Supported models: tts-1, tts-1-hd, kokoro",
|
|
"default": "kokoro"
|
|
},
|
|
"input": {
|
|
"type": "string",
|
|
"title": "Input",
|
|
"description": "The text to generate audio for"
|
|
},
|
|
"voice": {
|
|
"type": "string",
|
|
"title": "Voice",
|
|
"description": "The voice to use for generation. Can be a base voice or a combined voice name.",
|
|
"default": "af_heart"
|
|
},
|
|
"response_format": {
|
|
"type": "string",
|
|
"enum": [
|
|
"mp3",
|
|
"opus",
|
|
"aac",
|
|
"flac",
|
|
"wav",
|
|
"pcm"
|
|
],
|
|
"title": "Response Format",
|
|
"description": "The format to return audio in. Supported formats: mp3, opus, flac, wav, pcm. PCM format returns raw 16-bit samples without headers. AAC is not currently supported.",
|
|
"default": "mp3"
|
|
},
|
|
"speed": {
|
|
"type": "number",
|
|
"maximum": 4.0,
|
|
"minimum": 0.25,
|
|
"title": "Speed",
|
|
"description": "The speed of the generated audio. Select a value from 0.25 to 4.0.",
|
|
"default": 1.0
|
|
},
|
|
"stream": {
|
|
"type": "boolean",
|
|
"title": "Stream",
|
|
"description": "If true (default), audio will be streamed as it's generated. Each chunk will be a complete sentence.",
|
|
"default": true
|
|
},
|
|
"return_timestamps": {
|
|
"type": "boolean",
|
|
"title": "Return Timestamps",
|
|
"description": "If true (default), returns word-level timestamps in the response",
|
|
"default": true
|
|
},
|
|
"return_download_link": {
|
|
"type": "boolean",
|
|
"title": "Return Download Link",
|
|
"description": "If true, returns a download link in X-Download-Path header after streaming completes",
|
|
"default": false
|
|
},
|
|
"lang_code": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"title": "Lang Code",
|
|
"description": "Optional language code to use for text processing. If not provided, will use first letter of voice name."
|
|
},
|
|
"volume_multiplier": {
|
|
"anyOf": [
|
|
{
|
|
"type": "number"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"title": "Volume Multiplier",
|
|
"description": "A volume multiplier to multiply the output audio by.",
|
|
"default": 1.0
|
|
},
|
|
"normalization_options": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/components/schemas/NormalizationOptions"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"description": "Options for the normalization system",
|
|
"default": {
|
|
"normalize": true,
|
|
"unit_normalization": false,
|
|
"url_normalization": true,
|
|
"email_normalization": true,
|
|
"optional_pluralization_normalization": true,
|
|
"phone_normalization": true,
|
|
"replace_remaining_symbols": true
|
|
}
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"input"
|
|
],
|
|
"title": "CaptionedSpeechRequest",
|
|
"description": "Request schema for captioned speech endpoint"
|
|
},
|
|
"GenerateFromPhonemesRequest": {
|
|
"properties": {
|
|
"phonemes": {
|
|
"type": "string",
|
|
"title": "Phonemes",
|
|
"description": "Phoneme string to synthesize"
|
|
},
|
|
"voice": {
|
|
"type": "string",
|
|
"title": "Voice",
|
|
"description": "Voice ID to use for generation"
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"phonemes",
|
|
"voice"
|
|
],
|
|
"title": "GenerateFromPhonemesRequest",
|
|
"description": "Simple request for phoneme-to-speech generation"
|
|
},
|
|
"HTTPValidationError": {
|
|
"properties": {
|
|
"detail": {
|
|
"items": {
|
|
"$ref": "#/components/schemas/ValidationError"
|
|
},
|
|
"type": "array",
|
|
"title": "Detail"
|
|
}
|
|
},
|
|
"type": "object",
|
|
"title": "HTTPValidationError"
|
|
},
|
|
"NormalizationOptions": {
|
|
"properties": {
|
|
"normalize": {
|
|
"type": "boolean",
|
|
"title": "Normalize",
|
|
"description": "Normalizes input text to make it easier for the model to say",
|
|
"default": true
|
|
},
|
|
"unit_normalization": {
|
|
"type": "boolean",
|
|
"title": "Unit Normalization",
|
|
"description": "Transforms units like 10KB to 10 kilobytes",
|
|
"default": false
|
|
},
|
|
"url_normalization": {
|
|
"type": "boolean",
|
|
"title": "Url Normalization",
|
|
"description": "Changes urls so they can be properly pronounced by kokoro",
|
|
"default": true
|
|
},
|
|
"email_normalization": {
|
|
"type": "boolean",
|
|
"title": "Email Normalization",
|
|
"description": "Changes emails so they can be properly pronouced by kokoro",
|
|
"default": true
|
|
},
|
|
"optional_pluralization_normalization": {
|
|
"type": "boolean",
|
|
"title": "Optional Pluralization Normalization",
|
|
"description": "Replaces (s) with s so some words get pronounced correctly",
|
|
"default": true
|
|
},
|
|
"phone_normalization": {
|
|
"type": "boolean",
|
|
"title": "Phone Normalization",
|
|
"description": "Changes phone numbers so they can be properly pronouced by kokoro",
|
|
"default": true
|
|
},
|
|
"replace_remaining_symbols": {
|
|
"type": "boolean",
|
|
"title": "Replace Remaining Symbols",
|
|
"description": "Replaces the remaining symbols after normalization with their words",
|
|
"default": true
|
|
}
|
|
},
|
|
"type": "object",
|
|
"title": "NormalizationOptions",
|
|
"description": "Options for the normalization system"
|
|
},
|
|
"OpenAISpeechRequest": {
|
|
"properties": {
|
|
"model": {
|
|
"type": "string",
|
|
"title": "Model",
|
|
"description": "The model to use for generation. Supported models: tts-1, tts-1-hd, kokoro",
|
|
"default": "kokoro"
|
|
},
|
|
"input": {
|
|
"type": "string",
|
|
"title": "Input",
|
|
"description": "The text to generate audio for"
|
|
},
|
|
"voice": {
|
|
"type": "string",
|
|
"title": "Voice",
|
|
"description": "The voice to use for generation. Can be a base voice or a combined voice name.",
|
|
"default": "af_heart"
|
|
},
|
|
"response_format": {
|
|
"type": "string",
|
|
"enum": [
|
|
"mp3",
|
|
"opus",
|
|
"aac",
|
|
"flac",
|
|
"wav",
|
|
"pcm"
|
|
],
|
|
"title": "Response Format",
|
|
"description": "The format to return audio in. Supported formats: mp3, opus, flac, wav, pcm. PCM format returns raw 16-bit samples without headers. AAC is not currently supported.",
|
|
"default": "mp3"
|
|
},
|
|
"download_format": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string",
|
|
"enum": [
|
|
"mp3",
|
|
"opus",
|
|
"aac",
|
|
"flac",
|
|
"wav",
|
|
"pcm"
|
|
]
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"title": "Download Format",
|
|
"description": "Optional different format for the final download. If not provided, uses response_format."
|
|
},
|
|
"speed": {
|
|
"type": "number",
|
|
"maximum": 4.0,
|
|
"minimum": 0.25,
|
|
"title": "Speed",
|
|
"description": "The speed of the generated audio. Select a value from 0.25 to 4.0.",
|
|
"default": 1.0
|
|
},
|
|
"stream": {
|
|
"type": "boolean",
|
|
"title": "Stream",
|
|
"description": "If true (default), audio will be streamed as it's generated. Each chunk will be a complete sentence.",
|
|
"default": true
|
|
},
|
|
"return_download_link": {
|
|
"type": "boolean",
|
|
"title": "Return Download Link",
|
|
"description": "If true, returns a download link in X-Download-Path header after streaming completes",
|
|
"default": false
|
|
},
|
|
"lang_code": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"title": "Lang Code",
|
|
"description": "Optional language code to use for text processing. If not provided, will use first letter of voice name."
|
|
},
|
|
"volume_multiplier": {
|
|
"anyOf": [
|
|
{
|
|
"type": "number"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"title": "Volume Multiplier",
|
|
"description": "A volume multiplier to multiply the output audio by.",
|
|
"default": 1.0
|
|
},
|
|
"normalization_options": {
|
|
"anyOf": [
|
|
{
|
|
"$ref": "#/components/schemas/NormalizationOptions"
|
|
},
|
|
{
|
|
"type": "null"
|
|
}
|
|
],
|
|
"description": "Options for the normalization system",
|
|
"default": {
|
|
"normalize": true,
|
|
"unit_normalization": false,
|
|
"url_normalization": true,
|
|
"email_normalization": true,
|
|
"optional_pluralization_normalization": true,
|
|
"phone_normalization": true,
|
|
"replace_remaining_symbols": true
|
|
}
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"input"
|
|
],
|
|
"title": "OpenAISpeechRequest",
|
|
"description": "Request schema for OpenAI-compatible speech endpoint"
|
|
},
|
|
"PhonemeRequest": {
|
|
"properties": {
|
|
"text": {
|
|
"type": "string",
|
|
"title": "Text"
|
|
},
|
|
"language": {
|
|
"type": "string",
|
|
"title": "Language",
|
|
"default": "a"
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"text"
|
|
],
|
|
"title": "PhonemeRequest"
|
|
},
|
|
"PhonemeResponse": {
|
|
"properties": {
|
|
"phonemes": {
|
|
"type": "string",
|
|
"title": "Phonemes"
|
|
},
|
|
"tokens": {
|
|
"items": {
|
|
"type": "integer"
|
|
},
|
|
"type": "array",
|
|
"title": "Tokens"
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"phonemes",
|
|
"tokens"
|
|
],
|
|
"title": "PhonemeResponse"
|
|
},
|
|
"ValidationError": {
|
|
"properties": {
|
|
"loc": {
|
|
"items": {
|
|
"anyOf": [
|
|
{
|
|
"type": "string"
|
|
},
|
|
{
|
|
"type": "integer"
|
|
}
|
|
]
|
|
},
|
|
"type": "array",
|
|
"title": "Location"
|
|
},
|
|
"msg": {
|
|
"type": "string",
|
|
"title": "Message"
|
|
},
|
|
"type": {
|
|
"type": "string",
|
|
"title": "Error Type"
|
|
}
|
|
},
|
|
"type": "object",
|
|
"required": [
|
|
"loc",
|
|
"msg",
|
|
"type"
|
|
],
|
|
"title": "ValidationError"
|
|
}
|
|
}
|
|
}
|
|
}
|