{ "asyncapi": "3.0.0", "info": { "title": "T2A V2 WebSocket API", "version": "1.0.0", "description": "WebSocket API for real-time text-to-speech streaming using T2A V2 model", "contact": { "name": "MiniMax API Support", "email": "api@minimax.io" } }, "servers": { "production": { "host": "api.minimax.io", "protocol": "wss", "description": "Production WebSocket server for T2A V2 streaming", "security": [ { "type": "http", "scheme": "bearer", "bearerFormat": "JWT" } ] } }, "channels": { "t2a_v2_websocket": { "address": "/ws/v1/t2a_v2", "messages": { "receive_connected_success": { "$ref": "#/components/messages/ReceiveConnectedSuccess" }, "send_task_start": { "$ref": "#/components/messages/SendTaskStart" }, "receive_task_started": { "$ref": "#/components/messages/ReceiveTaskStarted" }, "send_task_continue": { "$ref": "#/components/messages/SendTaskContinue" }, "receive_task_continued": { "$ref": "#/components/messages/ReceiveTaskContinued" }, "send_task_finish": { "$ref": "#/components/messages/SendTaskFinish" }, "receive_task_finished": { "$ref": "#/components/messages/ReceiveTaskFinished" }, "receive_task_failed": { "$ref": "#/components/messages/ReceiveTaskFailed" } } } }, "operations": { "sendMessage": { "action": "receive", "channel": { "$ref": "#/channels/t2a_v2_websocket" }, "messages": [ { "$ref": "#/channels/t2a_v2_websocket/messages/send_task_start" }, { "$ref": "#/channels/t2a_v2_websocket/messages/send_task_continue" }, { "$ref": "#/channels/t2a_v2_websocket/messages/send_task_finish" } ], "summary": "" }, "receiveMessage": { "action": "send", "channel": { "$ref": "#/channels/t2a_v2_websocket" }, "messages": [ { "$ref": "#/channels/t2a_v2_websocket/messages/receive_connected_success" }, { "$ref": "#/channels/t2a_v2_websocket/messages/receive_task_started" }, { "$ref": "#/channels/t2a_v2_websocket/messages/receive_task_continued" }, { "$ref": "#/channels/t2a_v2_websocket/messages/receive_task_finished" }, { "$ref": "#/channels/t2a_v2_websocket/messages/receive_task_failed" } ], "summary": "" } }, "components": { "messages": { "ReceiveConnectedSuccess": { "name": "ReceiveConnectedSuccess", "title": "Connected Success Event", "summary": "Notification that T2A task has started", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/ReceiveConnectedSuccessEvent" }, "examples": [ { "payload": { "session_id": "xxxx", "event": "connected_success", "trace_id": "0303a2882bf18235ae7a809ae0f3cca7", "base_resp": { "status_code": 0, "status_msg": "success" } } } ] }, "SendTaskStart": { "name": "TaskStart", "title": "Task Start Event", "summary": "Sending the `\"task_start\"` event officially begins the speech synthesis task. The task is considered successfully started when the server returns a `\"task_started\"` event. Only after receiving this event can you send `\"task_continue\"` or `\"task_finish\"` events to the server.", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/SendTaskStartEvent" }, "examples": [ { "payload": { "event": "task_start", "model": "speech-2.8-turbo", "language_boost": "Chinese", "voice_setting": { "voice_id": "English_expressive_narrator", "speed": 1, "vol": 1, "pitch": 0 }, "pronunciation_dict": { "tone": ["Omg/Oh my god"] }, "audio_setting": { "sample_rate": 32000, "bitrate": 128000, "format": "mp3", "channel": 1 } } } ] }, "ReceiveTaskStarted": { "name": "ReceiveTaskStarted", "title": "Task Started Event", "summary": "Notification that T2A task has started", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/ReceiveTaskStartedEvent" }, "examples": [ { "payload": { "session_id": "xxxx", "event": "task_started", "trace_id": "0303a2882bf18235ae7a809ae0f3cca7", "base_resp": { "status_code": 0, "status_msg": "success" } } } ] }, "SendTaskContinue": { "name": "TaskContinue", "title": "Task Continue Event", "summary": "After receiving the `\"task_started\"` event from the server, the task officially begins. You can send `\"task_continue\"` events to provide text for synthesis. Multiple `\"task_continue\"` events can be sent sequentially. If no new event is sent within 120 seconds after receiving the last result, the WebSocket connection will automatically close.", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/SendTaskContinueEvent" }, "examples": [ { "payload": { "event": "task_continue", "text": "Omg(sighs), the real danger is not that computers start thinking like people, but that people start thinking like computers. Computers can only help us with simple tasks." } } ] }, "ReceiveTaskContinued": { "name": "ReceiveTaskContinued", "title": "Task Continued Event", "summary": "Notification that T2A task is continuing", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/ReceiveTaskContinuedEvent" }, "examples": [ { "payload": { "data": { "audio": "xxx" }, "extra_info": { "audio_channel": 1, "audio_format": "mp3", "audio_length": 9914, "audio_sample_rate": 32000, "audio_size": 157869, "bitrate": 128000, "invisible_character_ratio": 0, "usage_characters": 158, "word_count": 158 }, "is_final": true, "session_id": "301871346491491", "trace_id": "04ee3794e2c9e4a6d5f99e77742f06fd", "base_resp": { "status_code": 0, "status_msg": "success" } } } ] }, "SendTaskFinish": { "name": "TaskFinish", "title": "Task Finish Event", "summary": "When the server receives the `task_finish` event, it waits for all tasks in the current queue to complete, then closes the WebSocket connection and ends the session.", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/SendTaskFinishEvent" }, "examples": [ { "payload": { "event": "task_finish" } } ] }, "ReceiveTaskFinished": { "name": "ReceiveTaskFinished", "title": "Task Finished Event", "summary": "Notification that T2A task has completed successfully", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/ReceiveTaskFinishedEvent" }, "examples": [ { "payload": { "session_id": "xxxx", "event": "task_finished", "trace_id": "0303a2882bf18235ae7a809ae0f3cca7", "base_resp": { "status_code": 0, "status_msg": "success" } } } ] }, "ReceiveTaskFailed": { "name": "ReceiveTaskFailed", "title": "Task Failed Event", "summary": "If the `task_failed` event is received, it indicates that the task has failed. In this case, the WebSocket connection must be closed, and the error should be handled.", "contentType": "application/json", "payload": { "$ref": "#/components/schemas/ReceiveTaskFailedEvent" }, "examples": [ { "payload": { "session_id": "xxxx", "event": "task_failed", "trace_id": "0303a2882bf18235ae7a809ae0f3cca7", "base_resp": { "status_code": 1004, "status_msg": "XXXXXXX" } } } ] } }, "schemas": { "ReceiveConnectedSuccessEvent": { "type": "object", "properties": { "session_id": { "type": "string", "description": "The ID of the entire session." }, "event": { "type": "string", "const": "connected_success", "description": "The type of session event. Returns `connected_success` upon successful connection." }, "trace_id": { "type": "string", "description": "The ID of a single request within the session, useful for troubleshooting or feedback." }, "base_resp": { "$ref": "#/components/schemas/BaseResp" } } }, "SendTaskStartEvent": { "type": "object", "required": ["event", "model", "voice_setting"], "properties": { "event": { "type": "string", "enum": ["task_start"], "default": ["task_start"], "description": "Controls the instruction being sent. For this step, set to `task_start`." }, "model": { "type": "string", "description": "The model version to request.", "enum": [ "speech-2.8-hd", "speech-2.8-turbo", "speech-2.6-hd", "speech-2.6-turbo", "speech-02-hd", "speech-02-turbo", "speech-01-hd", "speech-01-turbo" ] }, "voice_setting": { "$ref": "#/components/schemas/VoiceSetting" }, "audio_setting": { "$ref": "#/components/schemas/AudioSetting" }, "pronunciation_dict": { "$ref": "#/components/schemas/PronunciationDict" }, "timbre_weights": { "$ref": "#/components/schemas/TimbreWeights" }, "language_boost": { "type": "string", "description": "Controls whether recognition for specific minority languages and dialects is enhanced. Default is `null`. If the language type is unknown, set to `\"auto\"` and the model will automatically detect it. \nSupported values: \n[`Chinese`, `Chinese,Yue`, `English`, `Arabic`, `Russian`, `Spanish`, `French`, `Portuguese`, `German`, `Turkish`, `Dutch`, `Ukrainian`, `Vietnamese`, `Indonesian`, `Japanese`, `Italian`, `Korean`, `Thai`, `Polish`, `Romanian`, `Greek`, `Czech`, `Finnish`, `Hindi`, `Bulgarian`, `Danish`, `Hebrew`, `Malay`, `Persian`, `Slovak`, `Swedish`, `Croatian`, `Filipino`, `Hungarian`, `Norwegian`, `Slovenian`, `Catalan`, `Nynorsk`, `Tamil`, `Afrikaans`, `auto`]\n\nNote: The speech-01 and speech-02 series models do not currently support Persian, Filipino, or Tamil.", "enum": [ "Chinese", "Chinese,Yue", "English", "Arabic", "Russian", "Spanish", "French", "Portuguese", "German", "Turkish", "Dutch", "Ukrainian", "Vietnamese", "Indonesian", "Japanese", "Italian", "Korean", "Thai", "Polish", "Romanian", "Greek", "Czech", "Finnish", "Hindi", "Bulgarian", "Danish", "Hebrew", "Malay", "Persian", "Slovak", "Swedish", "Croatian", "Filipino", "Hungarian", "Norwegian", "Slovenian", "Catalan", "Nynorsk", "Tamil", "Afrikaans", "auto" ] }, "text_normalization_mode": { "type": "string", "description": "Text normalization. `basic` uses fast, rule-based normalization. `quality` uses a hybrid LLM + rule-based approach to improve normalization quality, with additional latency. See [Text Normalization](/guides/speech-t2a-websocket#text-normalization).\n\nNote:\n- `quality` currently takes effect only for non-streaming HTTP requests. WebSocket synthesis is streaming, so `quality` is processed as `basic` here and no error is returned.\n- When this parameter is set, `voice_setting.text_normalization` and `voice_setting.english_normalization` are ignored. If it is omitted, those settings apply (disabled by default).", "enum": [ "basic", "quality" ], "x-mint": { "post": [ "updated" ] } }, "voice_modify": { "$ref": "#/components/schemas/VoiceModify" }, "subtitle_enable": { "type": "boolean", "description": "Controls whether subtitles are enabled. Default is `false`. Available for models: `speech-2.8-hd`, `speech-2.8-turbo`, `speech-2.6-hd`, `speech-2.6-turbo`, `speech-02-hd`, `speech-02-turbo`, `speech-01-hd`, `speech-01-turbo`.", "default": false }, "subtitle_type": { "type": "string", "description": "Subtitle granularity. Default is `sentence`. Options:\n- `sentence`: sentence-level timestamps\n- `word`: word-level timestamps\n- `word_streaming`: word-level timestamps optimized for streaming\n\nSubtitles are delivered in `data.subtitle` of `task_continued` events along with the audio; no subtitle file is provided:\n- `sentence` / `word`: returned once per segment, on the last audio chunk of that segment. `sentence` does not include `timestamped_words`\n- `word_streaming`: returned on every audio chunk, carrying the cumulative subtitle of the current segment so far (`timestamped_words` and `time_end` keep growing). Replace the previous result of the same segment with the latest one; a change of `text_begin` means a new segment has started\n\nMessages with `is_final: true` do not carry subtitles, so check `data.subtitle` on every `task_continued` message.", "enum": ["sentence", "word", "word_streaming"], "default": "sentence" }, "continuous_sound": { "type": "boolean", "description": "Controls model-side text segmentation strategy. Only available for `speech-2.8-hd` and `speech-2.8-turbo` models.\n- `true`: model does not split the text and performs continuous inference to generate audio (better prosody for long text)\n- `false`: model splits the text and runs concurrent inference for each segment (lower latency)\n\nDefault is `false`.", "default": false } } }, "ReceiveTaskStartedEvent": { "type": "object", "properties": { "session_id": { "type": "string", "description": "The id of the entire session." }, "event": { "type": "string", "const": "The type of session event. For this step, a successful response returns `task_started`." }, "trace_id": { "type": "string", "description": "The ID of a single request within the session, useful for troubleshooting or feedback." }, "base_resp": { "$ref": "#/components/schemas/TaskStartFinishBaseResp" } } }, "SendTaskContinueEvent": { "type": "object", "required": ["event", "text"], "properties": { "event": { "type": "string", "description": "The type of session event. For this step, set to `task_continue`.", "enum": ["task_continue"], "default": ["task_continue"] }, "text": { "type": "string", "description": "Text to be synthesized into speech. Maximum length: 10,000 characters.\n- Use line breaks (`\\n`) to indicate paragraph changes.\n- Pause control: Custom pauses between text segments can be specified. Insert `<#x#>` in the text, where `x` is the pause duration in seconds (range **[0.01, 99.99]**, up to two decimal places). Pause markers must be placed between pronounceable text segments; multiple consecutive pause markers are not allowed.\n- **Interjection tags**: Only supported when using `speech-2.8-hd` or `speech-2.8-turbo` models. Supported interjections: `(laughs)`, `(chuckle)`, `(coughs)`, `(clear-throat)`, `(groans)`, `(breath)`, `(pant)`, `(inhale)`, `(exhale)`, `(gasps)`, `(sniffs)`, `(sighs)`, `(snorts)`, `(burps)`, `(lip-smacking)`, `(humming)`, `(hissing)`, `(emm)`, `(sneezes)`." } } }, "ReceiveTaskContinuedEvent": { "type": "object", "properties": { "data": { "type": "object", "description": "`data` may return `null`. Please check for null when referencing example code.", "properties": { "audio": { "type": "string", "description": "Synthesized audio segment, hex-encoded, generated in the format defined in the request (mp3/ pcm/ flac)." }, "subtitle": { "type": "object", "description": "Returned when subtitles are enabled. Carries the subtitle of the current segment and is delivered with the corresponding audio chunk; see `subtitle_type` in `task_start` for timing. Not present on messages with `is_final: true`.", "properties": { "text": { "type": "string", "description": "Segment text." }, "text_begin": { "type": "integer", "format": "int64", "description": "Start character offset of the segment in the synthesized text (inclusive)." }, "text_end": { "type": "integer", "format": "int64", "description": "End character offset of the segment in the synthesized text (exclusive)." }, "time_begin": { "type": "number", "description": "Segment start time in milliseconds, relative to the start of the synthesized audio." }, "time_end": { "type": "number", "description": "Segment end time in milliseconds, relative to the start of the synthesized audio." }, "timestamped_words": { "type": "array", "description": "Word-level timestamps. Returned only when `subtitle_type` is `word` / `word_streaming`; `null` for `sentence`.", "items": { "type": "object", "properties": { "word": { "type": "string", "description": "Word text." }, "word_begin": { "type": "integer", "format": "int64", "description": "Start character offset of the word in the synthesized text (inclusive)." }, "word_end": { "type": "integer", "format": "int64", "description": "End character offset of the word in the synthesized text (exclusive)." }, "time_begin": { "type": "number", "description": "Word start time in milliseconds." }, "time_end": { "type": "number", "description": "Word end time in milliseconds." } } } } } } } }, "trace_id": { "type": "string", "description": "ID of the individual request within the session, useful for troubleshooting or feedback." }, "session_id": { "type": "string", "description": "ID of the entire session." }, "event": { "type": "string", "description": "Session event type. On success, returns `\"task_continued\"`." }, "is_final": { "type": "boolean", "description": "Indicates whether this response is the final one." }, "extra_info": { "$ref": "#/components/schemas/ExtraInfo" }, "base_resp": { "$ref": "#/components/schemas/TaskContinueBaseResp" } } }, "SendTaskFinishEvent": { "type": "object", "required": ["event"], "properties": { "event": { "type": "string", "enum": ["task_finish"], "default": ["task_finish"], "description": "The type of session event. For this step, set the value to `task_finish`." } } }, "ReceiveTaskFinishedEvent": { "type": "object", "properties": { "trace_id": { "type": "string", "description": "The ID of a single request within the session, useful for troubleshooting or feedback." }, "session_id": { "type": "string", "description": "ID of the entire session." }, "event": { "type": "string", "description": "Session event type. On success, returns `\"task_finished\"`." }, "base_resp": { "$ref": "#/components/schemas/TaskStartFinishBaseResp" } } }, "ReceiveTaskFailedEvent": { "type": "object", "properties": { "trace_id": { "type": "string", "description": "The ID of a single request within the session, useful for troubleshooting or feedback." }, "session_id": { "type": "string", "description": "ID of the entire session." }, "event": { "type": "string", "description": "Session event type. On success, returns `\"task_finished\"`." }, "base_resp": { "$ref": "#/components/schemas/TaskFailedBaseResp" } } }, "VoiceSetting": { "type": "object", "required": ["voice_id"], "properties": { "voice_id": { "type": "string", "description": "The ID of the target voice. \r\n- To apply mixed voices, configure the `timbre_weights` parameter and leave this value empty. \r\n- Supports system voices, cloned voices, and AI-generated voices. Below is a selection of the latest system voices (IDs). The full list of available voices can be viewed on the [System Voice ID List](/faq/system-voice-id) or retrieved programmatically using the [Get Voice API](/api-reference/voice-management-get). \r\n - Chinese:\r\n - moss_audio_ce44fc67-7ce3-11f0-8de5-96e35d26fb85\r\n - moss_audio_aaa1346a-7ce7-11f0-8e61-2e6e3c7ee85d\r\n - Chinese (Mandarin)_Lyrical_Voice\r\n - Chinese (Mandarin)_HK_Flight_Attendant\r\n\r\n - English:\r\n - English_Graceful_Lady\r\n - English_Insightful_Speaker\r\n - English_radiant_girl\r\n - English_Persuasive_Man\r\n - moss_audio_6dc281eb-713c-11f0-a447-9613c873494c\r\n - moss_audio_570551b1-735c-11f0-b236-0adeeecad052\r\n - moss_audio_ad5baf92-735f-11f0-8263-fe5a2fe98ec8\r\n - English_Lucky_Robot\r\n\r\n - Japanese:\r\n - Japanese_Whisper_Belle\r\n - moss_audio_24875c4a-7be4-11f0-9359-4e72c55db738\r\n - moss_audio_7f4ee608-78ea-11f0-bb73-1e2a4cfcd245\r\n - moss_audio_c1a6a3ac-7be6-11f0-8e8e-36b92fbb4f95" }, "speed": { "type": "number", "format": "float", "description": "Speech speed. Higher values result in faster speech.\nRange: `[0.5, 2]` (default: 1.0).", "minimum": 0.5, "maximum": 2.0, "default": 1.0 }, "vol": { "type": "number", "format": "float", "description": "Speech volume. Higher values increase loudness.\nRange: `(0, 10]` (default: `1.0`).", "exclusiveMinimum": 0, "maximum": 10.0, "default": 1.0 }, "pitch": { "type": "integer", "description": "Speech pitch adjustment.\nRange: `[-12, 12]` (default: `0`, original pitch).", "minimum": -12, "maximum": 12, "default": 0 }, "emotion": { "type": "string", "description": "Emotion control for synthesized speech. Supported values: `[\"happy\", \"sad\", \"angry\", \"fearful\", \"disgusted\", \"surprised\", \"calm\", \"fluent\", \"whisper\"]`. \r\n- By default, the model automatically selects the most natural emotion based on text. Manual specification is only recommended when explicitly needed. \r\n- Available for models: `speech-2.8-hd`, `speech-2.8-turbo`, `speech-2.6-hd`, `speech-2.6-turbo`, `speech-02-hd`, `speech-02-turbo`, `speech-01-hd`, `speech-01-turbo`. \r\n- Option `fluent`, `whisper` is only available for models: `speech-2.6-turbo`, `speech-2.6-hd`. `speech-2.8-hd` and `speech-2.8-turbo` do not support `whisper`.", "enum": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm", "fluent", "whisper" ] }, "english_normalization": { "type": "boolean", "description": "Deprecated. Use the top-level `text_normalization_mode` field of the `task_start` event instead: `true` is equivalent to `text_normalization_mode=basic`; `false` or omitted is equivalent to omitting `text_normalization_mode`. If both are set, `text_normalization_mode` takes precedence.\n\nEnable text normalization in English. Improves performance in digit-reading scenarios at the cost of slightly higher latency. Default: `false`.", "deprecated": true }, "text_normalization": { "type": "boolean", "description": "Deprecated. Use the top-level `text_normalization_mode` field of the `task_start` event instead: `true` is equivalent to `text_normalization_mode=basic`; `false` or omitted is equivalent to omitting `text_normalization_mode`. If both are set, `text_normalization_mode` takes precedence.\n\nEnable text normalization (Chinese/English). Improves performance in digit-reading scenarios at the cost of slightly higher latency. Default: `false`. If both this and `english_normalization` are set, this parameter takes precedence.", "default": false, "deprecated": true }, "latex_read": { "type": "boolean", "description": "Enable LaTeX formula reading. Default: `false`.\n\n- Only supports Chinese. When this parameter is enabled, `language_boost` will be set to `Chinese`.\n- Formulas must be wrapped with `$$`.\n- If the request contains a formula with `\"\\\"`, it must be escaped as `\"\\\\\"`.\n\nExample: The quadratic formula\n![The quadratic formula](https://filecdn.minimax.chat/public/d6f62e9a-cd3f-4f55-a237-257eef531683.png)\n\nshould be written as `$$x = \\\\frac{-b \\\\pm \\\\sqrt{b^2 - 4ac}}{2a}$$`" } } }, "AudioSetting": { "type": "object", "properties": { "sample_rate": { "type": "integer", "description": "Specifies the sampling rate of the generated audio. Supported values: `[8000, 16000, 22050, 24000, 32000, 44100]`. Default is `32000`." }, "bitrate": { "type": "integer", "description": "Specifies the bitrate of the generated audio. Supported values: `[32000, 64000, 128000, 256000]`. Default is `128000`.\n*Note: This parameter only applies to audio in `mp3` format.*" }, "format": { "type": "string", "description": "Specifies the format of the generated audio. Supported values: `[mp3, pcm, flac, wav, pcmu_raw, pcmu_wav, opus]`. Default is `mp3`.\n*Note: `pcmu_raw` and `pcmu_wav` are G.711 μ-law encoded (8 kHz sample rate; `pcmu_raw` is headerless raw, `pcmu_wav` is wrapped in a WAV container). `opus` is Ogg/Opus encoded; in streaming mode, audio chunks must be reassembled in arrival order before decoding.*", "enum": ["mp3", "wav", "flac", "pcm", "pcmu_raw", "pcmu_wav", "opus"] }, "channel": { "type": "integer", "description": "Specifies the number of audio channels. Supported values: `[1, 2]`. `1` = mono, `2` = stereo. Default is `1`." } } }, "PronunciationDict": { "type": "object", "properties": { "tone": { "type": "array", "items": { "type": "string" }, "description": "Defines pronunciation rules for specific characters or symbols.\nFor Chinese text, tones are represented numerically: 1 = first tone, 2 = second tone, 3 = third tone, 4 = fourth tone, 5 = neutral tone.\nExample: `[\"omg/oh my god\"]`" } } }, "TimbreWeights": { "type": "object", "properties": { "voice_id": { "type": "string", "description": "The ID of the voice used for synthesis. Must be specified together with `weight`.\nSupports system voices, cloned voices, and text-to-voice generated voices. The full list of available voices can be viewed on the [System Voice ID List](/faq/system-voice-id) or retrieved programmatically using the [Get Voice API](/api-reference/voice-management-get). " }, "weight": { "type": "integer", "description": "The weight assigned to each voice. Must be specified together with `voice_id`.\nSupported range: `[1, 100]`. Up to 4 voices can be mixed. A higher weight value increases similarity to the corresponding voice.\n\nParameter Configuration Example:\n\n```json\n\"timbre_weights\": [\n {\n \"voice_id\": \"female-chengshu\",\n \"weight\": 30\n },\n {\n \"voice_id\": \"female-tianmei\",\n \"weight\": 70\n }\n]\n```", "minimum": 1, "maximum": 100 } } }, "VoiceModify": { "type": "object", "description": "Voice effects configuration.\nSupported audio formats:\n1. Non-streaming: mp3, wav, flac\n2. Streaming: mp3", "properties": { "pitch": { "type": "integer", "description": "Corresponds to the “Deepen/Brighten” slider on the official page. Range: [-100, 100]. Values closer to -100 produce a deeper voice, while values closer to 100 result in a brighter tone.\n![pitch](https://filecdn.minimax.chat/public/75af719d-e126-4297-b3cb-416f382e04ec.png)", "minimum": -100, "maximum": 100 }, "intensity": { "type": "integer", "description": "Corresponds to the “Stronger/Softer” slider on the official page. Range: [-100, 100]. Values closer to -100 create a stronger, more forceful sound, while values closer to 100 yield a softer tone.\n![intensity](https://filecdn.minimax.chat/public/14015a81-d9c4-459b-9536-15c511aac6c0.png)", "minimum": -100, "maximum": 100 }, "timbre": { "type": "integer", "description": "Corresponds to the “Nasal/Crisp” slider on the official page. Range: [-100, 100]. Values closer to -100 produce a fuller, richer sound, while values closer to 100 generate a crisper tone.\n![timbre](https://filecdn.minimax.chat/public/86ab8ff8-896c-4254-b181-017d9d14000e.png)", "minimum": -100, "maximum": 100 }, "sound_effects": { "type": "string", "description": "Sound effects. Only one can be applied at a time. Options: `spacious_echo`, `auditorium_echo`, `lofi_telephone`,`robotic`", "enum": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ] } } }, "ExtraInfo": { "type": "object", "description": "Additional information.", "properties": { "audio_length": { "type": "integer", "format": "int64", "description": "Audio duration in milliseconds" }, "audio_sample_rate": { "type": "integer", "format": "int64", "description": "Audio sample rate" }, "audio_size": { "type": "integer", "format": "int64", "description": "Audio file size in bytes" }, "bitrate": { "type": "integer", "format": "int64", "description": "Audio bitrate" }, "audio_format": { "type": "string", "description": "Generated audio file format. Options: mp3/pcm/flac." }, "audio_channel": { "type": "integer", "format": "int64", "description": "Number of audio channels: 1 = mono, 2 = stereo." }, "invisible_character_ratio": { "type": "integer", "format": "float", "description": "Ratio of illegal characters. If ≤ 10%, audio is generated normally with the ratio returned. Above 10%, an error is triggered." }, "usage_characters": { "type": "integer", "format": "int64", "description": "Number of billing characters for this speech generation." }, "usage_voice_count": { "type": "integer", "format": "int64", "description": "Number of voices billed in this request (a voice is charged on its first use). Returned only when a voice fee is incurred." }, "word_count": { "type": "integer", "format": "int64", "description": "Number of characters in the synthesized text (punctuation and spaces included). For reference only and not used for billing; see `usage_characters` for billable characters." } } }, "BaseResp": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "Status code, where `0` indicates a successful connection.\nFor more information, please refer to the [Error Code Reference](/api-reference/errorcode)." }, "status_msg": { "type": "string", "description": "Detailed status message." } } }, "TaskStartFinishBaseResp": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "- 0: success\n- 2202: illegal event\nFor more information, please refer to the [Error Code Reference](/api-reference/errorcode)." }, "status_msg": { "type": "string", "description": "Detailed status message." } } }, "TaskContinueBaseResp": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "Status code.\n- 0: Request successful\n- 1000: Unknown error\n- 1001: Request timeout\n- 1002: Rate limit\n- 1004: Authentication failed\n- 1039: TPM rate limit triggered\n- 1042: Illegal characters > 10%\n- 2013: Invalid input parameters\n- 2201: Timeout disconnect\n- 2202: Illegal event\n- 2203: Empty text, skipped\n- 2204: Exceeded character limit, skipped\n- 2205: Request limit exceeded\nFor more codes, see [Error Codes](/api-reference/errorcode)." }, "status_msg": { "type": "string", "description": "Detailed status message." } } }, "TaskFailedBaseResp": { "type": "object", "properties": { "status_code": { "type": "integer", "description": "The status code.\n- `1000`: Unknown error\n- `1001`: Timeout\n- `1002`: Rate limit exceeded\n- `1004`: Authentication failed\n- `1039`: TPM rate limit triggered\n- `1042`: More than 10% invalid characters\n- `2013`: Invalid input format\n- `2201`: Timeout disconnection\nFor more codes, see [Error Codes](/api-reference/errorcode)." }, "status_msg": { "type": "string", "description": "Detailed status message." } } } } } }