TTS-MiniMax β
This page covers calling MiniMax speech synthesis through MPS. MiniMax is integrated under the engine code minimax: the APIs, authentication, billing, task polling and storage all reuse the existing MPS speech synthesis APIs β you only set "engine": "minimax" inside the ExtParam field to route to MiniMax, then add the model, emotion, speed and other parameters as needed.
MiniMax has the broadest API coverage of the external TTS engines: it supports speech synthesis, voice cloning and voice design at the same time, and offers seven emotions (emotion) plus independent volume and pitch control.
Choosing between the engines
- Need per-character timestamps for karaoke-style subtitles β TTS-ElevenLabs
- Need to describe accent and tone in one natural-language sentence β TTS-Gemini (
engineCustom.prompt) - Need scenario broadcast styles (news, advertising, radio, ASMRβ¦) β TTS-Seed
- Need custom emotion tags, or cloning without creating a voice β TTS-Fishaudio
- Need enumerated emotions (happy / sad / angry β¦), independent volume and pitch, or both cloning and design β this page
The full comparison of all seven engines is in MPS TTS Engines Compared.
APIs and official references β
All APIs below belong to the MPS "Media AI β Dubbing APIs" category. Official API references live under Media AI β Dubbing APIs on Tencent Cloud International.
APIs that support minimax β
The MiniMax engine integration guide explicitly lists these 7 APIs as switchable to MiniMax via ExtParam.engine:
| API | Purpose | Call type | Official reference |
|---|---|---|---|
TextToSpeech | Short text to speech, returns audio directly | Sync | 1041/82311 |
CloneVoice | Clone a voice from reference audio | Sync | 1041/82312 |
TextToSpeechAsync | Long text to speech, returns a TaskId | Async | 1041/79693 |
DescribeTextToSpeechAsyncTask | Poll async synthesis result (Status / AudioUrl) | Sync | 1041/79696 |
DesignVoiceAsync | Design a new voice from a text description, returns a TaskId | Async | 1041/79694 |
DescribeDesignTask | Poll voice design task result | Sync | 1041/79598 |
DescribeVoices | Query available voices (including MiniMax system voices) | Sync | 1041/79695 |
Other APIs in the same category β
| API | Purpose | Works with MiniMax | Official reference |
|---|---|---|---|
UpdateVoice / DeleteVoice | Update / delete a cloned or designed voice | β³ Not listed in the guide | 1041/81214 / 1041/81215 |
ChangeVoice | Voice conversion | β³ Not listed in the guide | 1041/83750 |
SyncDubbing | Legacy combined API (clone or synthesize) | β³ Not listed in the guide | 1041/77775 |
β³ = not mentioned in the integration guide; whether it can be switched to MiniMax should be confirmed by actual calls.
Shared conventions:
- Version
2019-06-12; endpointmps.intl.tencentcloudapi.comon International (mps.tencentcloudapi.comin the Chinese mainland). - Authentication is TC3-HMAC-SHA256 (SecretId / SecretKey); see Quick Start for the signing method.
- Rate limit is
20 requests/secondper API.
Comparison with the other engines β
MPS currently offers seven external TTS engines. The full side-by-side comparison (API coverage, emotion mechanism, audio parameters, cloning, selection guidance) is on the Blog: MPS TTS Engines Compared β the comparison table is maintained only there, so the engine pages cannot drift apart.
Where minimax sits: the broadest API coverage β synthesis, cloning and voice design are all supported, with independent control over emotion, volume and pitch.
Engine switching: ExtParam.engine β
The MPS speech synthesis APIs are engine-agnostic by themselves β the ExtParam JSON string decides which engine runs the request. Parameters come in three layers:
| Layer | Purpose | Notes |
|---|---|---|
engine | Selects the engine | Always minimax on this page |
synExt.* | MPS-normalized synthesis parameters | Model, emotion, format, speed β field names are unified across engines |
synExt.engineCustom.* | Pass-through to MiniMax's native parameters | Supports every parameter of the MiniMax official request body |
The outer layer wins
When the same key appears in both synExt.xxx and synExt.engineCustom.xxx, the outer synExt value takes effect. To use a MiniMax-only parameter, put it in engineCustom only β do not repeat it in synExt.
ExtParam is a string in the request, not an object β the JSON must be escaped and passed as a string (see Examples).
Key minimax parameters β
| Parameter | Type | Required | Description |
|---|---|---|---|
engine | String | Yes | Set to minimax |
synExt | Object | No | Synthesis extension parameters |
synExt.model | String | No | Model; supports speech-2.6-hd (default), speech-2.8-hd and others |
synExt.emotion | String | No | Emotion; see Emotion values |
synExt.format | String | No | Audio format: mp3, pcm, flac, wav, pcmu_raw, pcmu_wav, opus; default wav |
synExt.sampleRate | Integer | No | Sample rate: 8000, 16000, 22050, 24000, 32000, 44100; default 16000 |
synExt.duration | Float | No | Target audio duration |
synExt.speed | Float | No | Speech rate, range [0.5, 2], default 1.0 |
synExt.vol | Float | No | Volume, range (0, 10], default 1.0 |
synExt.pitch | Integer | No | Pitch, range [-12, 12], default 0 (original pitch) |
synExt.cutSilence | Bool | No | Trim leading/trailing silence; currently Chinese and English only |
synExt.engineCustom | Object | No | Engine-specific parameters. Passes through all official request parameters of the engine; the outer layer wins on conflicts |
Emotion values β
synExt.emotion has seven values and is MiniMax's main differentiator from the other two engines:
| Value | Meaning |
|---|---|
happy | Happy |
sad | Sad |
angry | Angry |
fearful | Fearful |
disgusted | Disgusted |
surprised | Surprised |
calm | Neutral |
How emotion, pitch and volume divide the work
emotion sets the emotional baseline for the whole clip, while pitch and vol are physical adjustments layered on top of it. For a "low and calm" narration, emotion: calm plus pitch: -3 sounds more natural than tuning pitch alone.
Voices (VoiceId) β
For MiniMax, VoiceId takes a MiniMax voice name directly, for example Chinese (Mandarin)_News_Anchor. Available voices can be queried with DescribeVoices β see Querying system voices.
Parameter example β
A complete ExtParam object (expanded for readability; it must be escaped into a string when sent):
{
"engine": "minimax",
"synExt": {
"model": "speech-2.6-hd",
"emotion": "happy",
"speed": 0.9,
"engineCustom": {
"pronunciation_dict": {
"tone": [
"ε€η/(chu3)(li3)",
"ζ±δΊ¬/γγ¦γγ§γ¦"
]
},
"subtitle_enable": false
}
}
}The two engineCustom fields here are MiniMax-only capabilities:
pronunciation_dict.tone: custom pronunciation.ε€η/(chu3)(li3)uses toned pinyin to pin down a heteronym, whileζ±δΊ¬/γγ¦γγ§γ¦uses kana to specify the reading of Japanese kanji.subtitle_enable: whether to output a subtitle file.
Examples β
Speech synthesis β TextToSpeech β
{
"Text": "ζ¨ε₯½",
"VoiceId": "Chinese (Mandarin)_News_Anchor",
"ExtParam": "{\"engine\":\"minimax\",\"synExt\":{\"model\":\"speech-2.6-hd\",\"emotion\":\"happy\",\"speed\":0.9}}"
}Note that the value of ExtParam is an escaped JSON string, not a nested object.
Voice cloning β CloneVoice β
{
"AudioData": "base64-encoded audio",
"ExtParam": "{\"engine\":\"minimax\"}"
}Cloning only needs the engine; synExt is unnecessary β synthesis parameters are supplied later when calling TextToSpeech.
Async synthesis and polling β
For long text, submit with TextToSpeechAsync β the ExtParam format is identical to the sync API β and it returns a TaskId. Then poll Status with DescribeTextToSpeechAsyncTask and read the audio from AudioUrl once it completes.
Querying system voices β
Use DescribeVoices (1041/79695) to query the voices available for MiniMax. ExtParam only needs the engine:
{
"engine": "minimax"
}Here too, ExtParam is passed as a JSON string. The API also supports filtering; common parameters:
| Parameter | Type | Description |
|---|---|---|
VoiceType | String | system / clone / design / all (default) |
Gender | String | male / female / unknown |
Age | String | child / teenager / youth / middle_aged / senior / unknown |
Languages.N | Array of String | Language |
Labels.N | Array of String | Tag |
PageNum / PageSize | Integer | Pagination; leaving PageSize empty returns all matching data |
Finding your own cloned voices
Cloned and designed voices are queried through the same API β set VoiceType to clone or design. Omitting it defaults to all, which returns everything.
Limits and gotchas β
ExtParamis a string: it must be an escaped JSON string in the request; passing an object is rejected as a parameter error.- The outer layer wins:
synExt.xxxoverridessynExt.engineCustom.xxxβ never write the same parameter in both layers. cutSilenceis Chinese/English only: it has no effect for other languages.- The default format is
wav, notmp3β setformatexplicitly when size matters. - The default sample rate is
16000: request44100explicitly for music or high-fidelity scenarios. - Volume is an open interval
(0, 10]:0is invalid; the minimum must be greater than 0. - APIs marked β³ should be confirmed by actual calls: the β / β³ marks follow what the MiniMax engine integration guide lists, and an unlisted API is not necessarily unavailable.
Related documents β
| Document | Notes |
|---|---|
| MPS TTS Engines Compared | Capabilities, parameters and selection guidance across all seven external engines |
| AI Dubbing | Overview of MPS dubbing and its built-in engines |
| TTS-ElevenLabs | The ElevenLabs engine (tts-l1) on the same APIs, with per-character timestamps |
| TTS-Gemini | The Google Gemini-TTS engine (tts-gg) on the same APIs, style controlled by prompt, no cloning |
| TTS-Seed | The TTS-Seed engine (tts-s) on the same APIs, with 24 emotion values |
| TTS-Fishaudio | The Fish Audio engine (tts-f) on the same APIs, with inline emotion tags and zero-shot cloning |
| TTS-Index | The same APIs on IndexTTS (index-tts): a reference audio URL straight in VoiceId, 8-dimension emotion vector |
| TTS-Seedaudio | The same APIs on Seed Audio (tts-sa): the only engine that generates speech from an image, word-level timestamps |
| MiniMax Music | MiniMax's music generation capability β a different API from the speech synthesis here |
| Quick Start | Authentication and request signing |
| Media AI β Dubbing APIs | Official API category |