curl --request POST \
  --url https://api.modellix.ai/api/v1/alibaba/cosyvoice-v3-flash \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "There is a large garden behind my house.",
  "voice": "longanyang"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-cosyvoice-v3-flash-001",
    "model_id": "alibaba/cosyvoice-v3-flash",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-cosyvoice-v3-flash-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: voice is required for alibaba/cosyvoice-v3-plus"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

CosyVoice v3 Flash

[Core Function] CosyVoice v3 Flash is Alibaba’s low-latency text-to-speech model. [Strengths] Rich system voice catalog, fixed-format instruction on Instruct-capable system voices, SSML, hot_fix, AIGC watermark, Markdown filter (cloned voices only), and multiple audio formats with faster turnaround than Plus. [Best For] Voice assistants, interactive prompts, IVR, short announcements, dialect system voices, and latency-sensitive batch TTS. [Limitations] Do NOT use when maximum speech quality or long-form audiobook fidelity is the priority (use Plus). System-voice instruction must follow CosyVoice voice-list fixed Chinese formats. [Routing] Choose Flash when speed or a richer system-voice catalog matters most. Choose Plus for premium narration quality.

POST

alibaba

cosyvoice-v3-flash

curl --request POST \
  --url https://api.modellix.ai/api/v1/alibaba/cosyvoice-v3-flash \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "text": "There is a large garden behind my house.",
  "voice": "longanyang"
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-cosyvoice-v3-flash-001",
    "model_id": "alibaba/cosyvoice-v3-flash",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-cosyvoice-v3-flash-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: voice is required for alibaba/cosyvoice-v3-plus"
}

{
  "code": 401,
  "message": "Authentication failed: invalid API key"
}

{
  "code": 429,
  "message": "Rate limit exceeded: 100 requests per minute, retry after 60 seconds"
}

{
  "code": 500,
  "message": "Internal server error"
}

Authorizations

Authorization

string

header

required

Modellix API Key. Format: Bearer <your_api_key>

Body

application/json

Shared CosyVoice v3 TTS request fields. Submit as an async task; poll GET /api/v1/tasks/{task_id} for the audio URL in result.resources.

text

string

required

Text to synthesize. Required. Max 20,000 Unicode characters. Supports plain text, SSML (set enable_ssml to true), and LaTeX formulas per Alibaba documentation.

Required string length: 1 - 20000

Example:

"There is a large garden behind my house."

voice

string

required

System or cloned voice ID for cosyvoice-v3-flash. Full official CosyVoice voice catalog (use only voices listed under cosyvoice-v3-flash for system voices): https://help.aliyun.com/zh/model-studio/cosyvoice-voice-list . Do not mix Plus and Flash system voices. Cloned or designed voice IDs are also accepted. Sample system voices (not exhaustive): longanyang, longhuhu_v3, longpaopao_v3, longshanshan_v3, longjiaxin_v3, loongkyong_v3, longfei_v3, longyingxiao_v3, longyingxun_v3, longxiaochun_v3, longantai_v3, longmiao_v3, longjiqi_v3, longanran_v3, longshuo_v3.

Required string length: 1 - 256

Example:

"longanyang"

format

enum<string>

default:mp3

Audio encoding format. Default mp3.

Available options:

mp3,

pcm,

wav,

opus

Example:

"mp3"

sample_rate

enum<integer>

default:22050

Audio sample rate in Hz. Default 22050.

Available options:

8000,

16000,

22050,

24000,

44100,

48000

Example:

24000

volume

integer

default:50

Output volume. Default 50. Range 0 (silent) to 100 (maximum).

Required range: 0 <= x <= 100

Example:

50

rate

number

default:1

Speech rate multiplier. Default 1.0. Range 0.5 (slow) to 2.0 (fast).

Required range: 0.5 <= x <= 2

Example:

1

pitch

number

default:1

Pitch multiplier. Default 1.0. Range 0.5 (lower) to 2.0 (higher).

Required range: 0.5 <= x <= 2

Example:

1

bit_rate

integer

Audio bit rate in kbps. Optional. Range 6 to 510. Only supported when format is opus; do not use for mp3, pcm, or wav.

Required range: 6 <= x <= 510

Example:

32

instruction

string

Optional speaking-style instruction for Instruct-capable system voices. Enforced weighted length ≤100 (CJK ideographs / Han count as 2; other characters count as 1). Alibaba requires fixed Chinese formats from the CosyVoice voice list for system voices.

Example:

"Speak in a friendly customer-service tone."

language_hint

enum<string>

Target language hint for pronunciation (numbers, symbols, minor languages).

Available options:

zh,

en,

fr,

de,

ja,

ko,

ru,

pt,

th,

id,

vi,

es,

it,

ms,

fil,

ar

Example:

"en"

seed

integer

default:0

Random seed for reproducible synthesis when text, voice, and other parameters are identical. Default 0. Range 0 to 65535.

Required range: 0 <= x <= 65535

Example:

0

enable_ssml

boolean

default:false

Whether to parse text as SSML. Default false. When true, text must follow Alibaba CosyVoice SSML rules.

Example:

false

hot_fix

object

Text hot-fix before synthesis. Optional object with pronunciation (custom pinyin for Chinese words) and replace (text substitution) arrays per Alibaba HTTP API.

Example:

{ "replace": [{ "Modellix": "Modelix" }] }

enable_aigc_tag

boolean

default:false

Embed AIGC invisible watermark into wav/mp3/opus output. Supported on cosyvoice-v3-plus and cosyvoice-v3-flash.

aigc_propagator

string

AIGC ContentPropagator. Only effective when enable_aigc_tag is true.

aigc_propagate_id

string

AIGC PropagateID. Only effective when enable_aigc_tag is true.

enable_markdown_filter

boolean

default:false

Filter Markdown markers before synthesis. Only supported on cosyvoice-v3-flash with cloned voices.

Response

Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result.

Response object for asynchronous task submission.

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; audio appears in result.resources.

Show child attributes

Cosyvoice v3 plus Qwen audio 3 0 tts plus

Model API

Common API

File API

CosyVoice v3 Flash

Authorizations

Body

Response