{ "openapi": "3.1.0", "info": { "title": "MiniMax T2A API", "description": "MiniMax Text-to-Audio API with support for streaming and non-streaming output", "license": { "name": "MIT" }, "version": "1.0.0" }, "servers": [ { "url": "https://api.minimax.io" } ], "security": [ { "bearerAuth": [] } ], "paths": { "/v1/t2a_v2": { "post": { "summary": "Text to Audio V2", "description": "", "operationId": "t2aV2", "tags": ["Text to Audio"], "parameters": [ { "name": "Content-Type", "in": "header", "required": true, "description": "The media type of the request body. Must be set to `application/json` to ensure the data is sent in JSON format.", "schema": { "type": "string", "enum": ["application/json"], "default": "application/json" } } ], "requestBody": { "description": "", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/T2aV2Req" }, "examples": { "Request(Non-streaming)": { "value": { "model": "speech-2.8-hd", "text": "Omg(sighs), the real danger is not that computers start thinking like people, but that people start thinking like computers. Computers can only help us with simple tasks.", "stream": false, "language_boost": "auto", "output_format": "hex", "voice_setting": { "voice_id": "English_expressive_narrator", "speed": 1.0, "vol": 1.0, "pitch": 0 }, "pronunciation_dict": { "tone": ["Omg/Oh my god"] }, "audio_setting": { "sample_rate": 32000, "bitrate": 128000, "format": "mp3", "channel": 1 }, "voice_modify": { "pitch": 0, "intensity": 0, "timbre": 0, "sound_effects": "spacious_echo" } } }, "Request(Streaming)": { "value": { "model": "speech-2.8-hd", "text": "Omg(sighs), the real danger is not that computers start thinking like people, but that people start thinking like computers. Computers can only help us with simple tasks.", "stream": true, "language_boost": "auto", "output_format": "hex", "voice_setting": { "voice_id": "English_expressive_narrator", "speed": 1.0, "vol": 1.0, "pitch": 0 }, "pronunciation_dict": { "tone": ["Omg/Oh my god"] }, "audio_setting": { "sample_rate": 32000, "bitrate": 128000, "format": "mp3", "channel": 1 }, "voice_modify": { "pitch": 0, "intensity": 0, "timbre": 0, "sound_effects": "spacious_echo" } } } } } }, "required": true }, "responses": { "200": { "description": "", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/T2aV2Resp" }, "examples": { "Request(Non-streaming)": { "value": { "data": { "audio": "", "status": 2 }, "extra_info": { "audio_length": 11124, "audio_sample_rate": 32000, "audio_size": 179926, "bitrate": 128000, "word_count": 163, "invisible_character_ratio": 0, "usage_characters": 163, "audio_format": "mp3", "audio_channel": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "success" } } }, "Request(Streaming)": { "value": [ { "data": { "audio": "hex encoded audio", "status": 2 }, "extra_info": { "audio_length": 12910, "audio_sample_rate": 32000, "audio_size": 205677, "bitrate": 128000, "word_count": 163, "invisible_character_ratio": 0, "usage_characters": 163, "audio_format": "mp3", "audio_channel": 1 }, "trace_id": "04ece790375f3ca2edbb44e8c4c200bf", "base_resp": { "status_code": 0, "status_msg": "success" } }, { "data": { "audio": "hex encoded audio_chunk3", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } }, { "data": { "audio": "hex encoded audio_chunk2", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } }, { "data": { "audio": "hex encoded audio_chunk1", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } } ] } } }, "text/event-stream": { "schema": { "$ref": "#/components/schemas/T2aV2Resp" }, "examples": { "Request(Streaming)": { "value": [ { "data": { "audio": "hex encoded audio", "status": 2 }, "extra_info": { "audio_length": 12910, "audio_sample_rate": 32000, "audio_size": 205677, "bitrate": 128000, "word_count": 163, "invisible_character_ratio": 0, "usage_characters": 163, "audio_format": "mp3", "audio_channel": 1 }, "trace_id": "04ece790375f3ca2edbb44e8c4c200bf", "base_resp": { "status_code": 0, "status_msg": "success" } }, { "data": { "audio": "hex encoded audio_chunk3", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } }, { "data": { "audio": "hex encoded audio_chunk2", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } }, { "data": { "audio": "hex encoded audio_chunk1", "status": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "" } } ] } } } } } } } } }, "components": { "schemas": { "Error": { "type": "object", "required": ["error", "message"], "properties": { "error": { "type": "integer", "format": "int32", "description": "Error code" }, "message": { "type": "string", "description": "Error message" } } }, "T2aV2Req": { "type": "object", "required": ["model", "text"], "properties": { "model": { "type": "string", "description": "The speech synthesis model version to use.", "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" ] }, "text": { "type": "string", "description": "The text to be converted into speech. Must be less than 10,000 characters.\n\n- For texts over 3,000 characters, streaming output is recommended.\n- Paragraph breaks should be marked with newline characters.\n\n- **Pause control**: You can customize speech pauses by adding markers in the form `<#x#>`, where `x` is the pause duration in seconds. Valid range: `[0.01, 99.99]`, up to two decimal places. Pause markers must be placed between speakable text segments and cannot be used consecutively.\n\n- **Inline pronunciation**: Wrap Mandarin Pinyin (with tone number `1–5`) or IPA symbols or Cantonese Jyutping (with tone number `1–6`) in half-width parentheses to override pronunciation of the target word or polyphonic character.\n - `\"The word live is pronounced (lɪv) as a verb and (laɪv) as an adjective.\"`\n - `\"This is (he2)平, not (huo4)面.\"`\n - `\"去街市買啲(sung3)。\"`\n\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)`." }, "stream": { "type": "boolean", "description": "Whether to enable streaming output. Defaults to `false`." }, "stream_options": { "$ref": "#/components/schemas/T2AStreamOption" }, "voice_setting": { "$ref": "#/components/schemas/T2AVoiceSetting" }, "audio_setting": { "$ref": "#/components/schemas/T2AAudioSetting" }, "pronunciation_dict": { "$ref": "#/components/schemas/PronunciationDict" }, "timbre_weights": { "type": "array", "description": "Timbre weights (legacy field)", "items": { "$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.\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" ], "default": null }, "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 requests (`stream=false`) with `speech-2.8-hd`, `speech-2.8-turbo`, `speech-2.6-hd`, and `speech-2.6-turbo`. For streaming requests or other models, `quality` is processed as `basic` and no error is returned.\n- When this parameter is set, `voice_setting.text_normalization` is ignored. If it is omitted, the `voice_setting.text_normalization` setting applies (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, only valid when `stream=true`\n\nIn streaming mode (`stream=true`), subtitles are delivered in `data.subtitle` along with the audio, and `subtitle_file` is not returned:\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\nIn non-streaming mode, subtitles are returned as a file via `subtitle_file`.", "enum": ["sentence", "word", "word_streaming"], "default": "sentence" }, "output_format": { "type": "string", "description": "Controls the output format. Options: `[url, hex]`. Default is `hex`. Only effective in non-streaming scenarios. In streaming, only `hex` is supported. Returned url is valid for 24 hours.", "enum": ["url", "hex"], "default": "hex" } } }, "T2ASubtitle": { "type": "object", "description": "Segment subtitle. The engine splits the text into segments (usually one sentence each); each segment has one subtitle entry.", "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": { "$ref": "#/components/schemas/T2ASubtitleWord" } } } }, "T2ASubtitleWord": { "type": "object", "description": "Word-level timestamp.", "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." } } }, "T2aV2Resp": { "type": "object", "properties": { "data": { "type": "object", "description": "The synthesized audio data object. The returned data object may be null, so a null check is required.", "properties": { "audio": { "type": "string", "description": "The synthesized audio data, encoded in hexadecimal, with a format consistent with the output format specified in the request." }, "subtitle_file": { "type": "string", "description": "Download link for generated subtitles. Subtitles are aligned to sentences (≤ 50 characters), timestamped in milliseconds, returned in JSON format Returned only for non-streaming requests (`stream=false`); for streaming, use `subtitle` / `subtitles`." }, "subtitle": { "description": "Returned in streaming mode (`stream=true`) when subtitles are enabled. Carries the subtitle of the current segment and is delivered with the corresponding audio chunk. Timing depends on `subtitle_type`: `sentence` / `word` are returned once on the last audio chunk of each segment; `word_streaming` returns the cumulative result of the current segment on every audio chunk.", "allOf": [ { "$ref": "#/components/schemas/T2ASubtitle" } ] }, "subtitles": { "type": "array", "description": "Returned in streaming mode (`stream=true`) when subtitles are enabled, in the last packet (`status=2`). Aggregates the subtitles of all segments in this request.", "items": { "$ref": "#/components/schemas/T2ASubtitle" } }, "status": { "type": "integer", "description": "Current audio stream status.\n\n`1`: synthesizing\n`2`: synthesis completed" } } }, "trace_id": { "type": "string", "description": "The session ID, used for troubleshooting and support." }, "extra_info": { "type": "object", "description": "Additional audio 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": "File size in bytes." }, "bitrate": { "type": "integer", "format": "int64", "description": "Audio bitrate." }, "audio_format": { "type": "string", "description": "Output audio format. Options: [mp3, pcm, flac].", "enum": ["mp3", "pcm", "flac"] }, "audio_channel": { "type": "integer", "format": "int64", "description": "Number of channels. 1 for mono , 2 for stereo." }, "invisible_character_ratio": { "type": "number", "format": "float64", "description": "Proportion of invalid characters.\nIf ≤ 10%, audio is generated normally and the ratio is returned.\nIf > 10%, an error is returned." }, "usage_characters": { "type": "integer", "format": "int64", "description": "Number of billable characters used in this synthesis." }, "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." }, "norm_text_char_count": { "type": "integer", "format": "int64", "description": "Number of characters processed by high-quality text normalization in this request (counted in Unicode characters). Returned only for non-streaming requests with `text_normalization_mode=quality`; `0` means high-quality normalization was not performed (for example, the model does not support it). For reference only and currently not used for billing." } } }, "base_resp": { "type": "object", "description": "Status code and details of this request.", "properties": { "status_code": { "type": "integer", "format": "int64", "description": "Status code.\n\n`0`: success\n`1000`: unknown error\n`1001`: timeout\n`1002`: rate limit exceeded\n`1004`: authentication failed\n`1039`: TPM rate limit exceeded\n`1042`: invalid characters exceed `10%`\n`2013`: invalid input parameters\n\nFor more details, see [Error Code Reference](/api-reference/errorcode)." }, "status_msg": { "type": "string", "description": "Status description." } } } }, "example": { "data": { "audio": "", "status": 2 }, "extra_info": { "audio_length": 11124, "audio_sample_rate": 32000, "audio_size": 179926, "bitrate": 128000, "word_count": 163, "invisible_character_ratio": 0, "usage_characters": 163, "audio_format": "mp3", "audio_channel": 1 }, "trace_id": "01b8bf9bb7433cc75c18eee6cfa8fe21", "base_resp": { "status_code": 0, "status_msg": "success" } } }, "T2AVoiceSetting": { "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\r\n\r\n - Cantonese (set `language_boost` to `Chinese,Yue`):\r\n - Cantonese_GentleLady\r\n - Cantonese_podacast_host_1" }, "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" ] }, "text_normalization": { "type": "boolean", "description": "Deprecated. Use the top-level `text_normalization_mode` parameter 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.", "default": false, "deprecated": true }, "latex_read": { "type": "boolean", "description": "Enable LaTeX formula reading.\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}$$`", "default": false } } }, "T2AAudioSetting": { "type": "object", "properties": { "sample_rate": { "type": "integer", "format": "int64", "description": "Specifies the sampling rate of the generated audio. Supported values: [`8000`, `16000`, `22050`, `24000`, `32000`, `44100`]." }, "bitrate": { "type": "integer", "format": "int64", "description": "Specifies the bitrate of the generated audio. Supported values: [`32000`, `64000`, `128000`, `256000`]. \nNote: 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`].\nNote: `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.", "enum": ["mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus"], "default": "mp3" }, "channel": { "type": "integer", "format": "int64", "description": "Specifies the number of audio channels. Supported values: [`1`, `2`].\n`1` = mono\n`2` = stereo\nDefault is `1`." }, "force_cbr": { "type": "boolean", "description": "Constant Bitrate (CBR) Control\nSet to `true` to enable Constant Bitrate (CBR) for audio encoding.\n\nNote: This parameter only takes effect when output is **streamed** in **MP3** format.", "default": false } } }, "PronunciationDict": { "type": "object", "properties": { "tone": { "type": "array", "description": "Defines custom pronunciation rules in `original/replacement` format. The replacement can be plain text, pinyin with tone numbers in parentheses, IPA in parentheses, or Japanese kana (hiragana, katakana, romaji — mixable). Multiple rules are applied simultaneously.\n\nExample:\n```json dark\n\"pronunciation_dict\": {\n \"tone\": [\n \"resume/(rɪˈzjuːm)\",\n \"read/(riːd)\",\n \"处理/(chu3)(li3)\",\n \"郑栅洁/(zheng4)(shan1)杰\",\n \"20日/はつか\",\n \"4桁/よんけた\",\n \"東京/トウキョウ\",\n \"omg/oh my god\",\n \"の/no\"\n ]\n}\n```\n\nThis single dictionary demonstrates: IPA for English polyphonic words, pinyin with tone numbers for Chinese, mixed pinyin + characters, Japanese hiragana/katakana for date counters and kanji, text-to-text expansion, and symbol substitution.\n\nChinese tones: `1` = first, `2` = second, `3` = third, `4` = fourth, `5` = neutral.", "items": { "type": "string" } } } }, "TimbreWeights": { "type": "object", "required": ["voice_id", "weight"], "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", "format": "int64", "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\n- Parameter Configuration Example:\n```json dark\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 } }, "example": { "voice_id": "female-chengshu", "weight": 30 } }, "VoiceModify": { "type": "object", "description": "Voice effects configuration.\n\nSupported audio formats:\n- Non-streaming: `mp3`, `wav`, `flac`\n- 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\n![pitch adjustment](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\n![intensity adjustment](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\n![timbre adjustment](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" ] } } }, "T2AStreamOption": { "type": "object", "properties": { "exclude_aggregated_audio": { "type": "boolean", "description": "Determines whether the final chunk should contain aggregated hex-encoded audio data. Default to false, which means the last chunk will include the complete audio." } } } }, "securitySchemes": { "bearerAuth": { "type": "http", "scheme": "bearer", "bearerFormat": "JWT", "description": "`HTTP: Bearer Auth`\n- Security Scheme Type: http\n- HTTP Authorization Scheme: `Bearer API_key`, can be found in [Account Management>API Keys](https://platform.minimax.io/user-center/basic-information/interface-key)." } } } }