> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Qwen Audio 3.1 TTS Flash Speech Synthesis
> - Convert text to speech, up to `5000` characters per request
- Choose from 68 system voices; see the [voice list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices). You can also use a voice you created with [Voice Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment), through cloning or design
- Custom voices expire by default `6 hours` after the creation task completes; synthesis after expiry returns `404` (`voice_expired`). Create a new voice with Voice Enrollment
- Supports natural-language instructions (`instruction`), inline emotion and paralinguistic tags, SSML, and custom pronunciation (`hot_fix`)
- Only the parameters listed below are accepted; other parameters return `400` (`unsupported_parameter`)
- Asynchronous processing; use the returned task ID to [query the result](/en/api-manual/task-management/get-task-detail)
- Tasks cannot be canceled after submission
- Generated audio links are valid for 24 hours; save them promptly
**Billing:**
- Billed by actual token usage: input tokens (related to text length) and output tokens (related to generated audio duration) are priced separately
- Credits are reserved at submission based on text length (`usage.credits_reserved`). On completion, billing is settled against actual usage: excess is refunded and any shortfall is charged. Failed tasks receive a full refund
- Numbers, letters, and symbols may be read individually, producing much longer audio and more output tokens than ordinary prose of the same length; actual usage may exceed the reservation
- For the same text, instructions or tags that slow delivery (such as `[very slowly]`) can substantially increase output tokens. Adjusting `speech_rate` and inserting SSML pauses do not increase output tokens
**Task result (when `status` is `completed`):**
| Field | Description |
|---|---|
| `results[0]` | Audio URL |
| `result_data[0].audio_url` | Audio URL, identical to `results[0]` |
| `result_data[0].format` | Audio format |
| `result_data[0].sample_rate` | Sample rate (Hz) |
| `usage.input_tokens` / `usage.output_tokens` / `usage.total_tokens` | Token usage for this synthesis |
| `usage.credits_used` | Actual credits used |
## OpenAPI
````yaml en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash.json POST /v1/audios/generations
openapi: 3.1.0
info:
title: Qwen Audio 3.1 TTS Flash Speech Synthesis API
description: >-
Convert text to speech with 68 system voices, natural-language instructions,
emotion tags, SSML, and custom pronunciation. Billing is based on actual
token usage.
license:
name: MIT
version: 1.0.0
servers:
- url: https://api.evolink.ai
description: Production environment
security:
- bearerAuth: []
tags:
- name: Speech Synthesis
description: Qwen Audio 3.1 TTS Flash speech synthesis endpoints
paths:
/v1/audios/generations:
post:
tags:
- Speech Synthesis
summary: Qwen Audio 3.1 TTS Flash Speech Synthesis
description: >-
- Convert text to speech, up to `5000` characters per request
- Choose from 68 system voices; see the [voice
list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices).
You can also use a voice you created with [Voice
Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment),
through cloning or design
- Custom voices expire by default `6 hours` after the creation task
completes; synthesis after expiry returns `404` (`voice_expired`).
Create a new voice with Voice Enrollment
- Supports natural-language instructions (`instruction`), inline emotion
and paralinguistic tags, SSML, and custom pronunciation (`hot_fix`)
- Only the parameters listed below are accepted; other parameters return
`400` (`unsupported_parameter`)
- Asynchronous processing; use the returned task ID to [query the
result](/en/api-manual/task-management/get-task-detail)
- Tasks cannot be canceled after submission
- Generated audio links are valid for 24 hours; save them promptly
**Billing:**
- Billed by actual token usage: input tokens (related to text length)
and output tokens (related to generated audio duration) are priced
separately
- Credits are reserved at submission based on text length
(`usage.credits_reserved`). On completion, billing is settled against
actual usage: excess is refunded and any shortfall is charged. Failed
tasks receive a full refund
- Numbers, letters, and symbols may be read individually, producing much
longer audio and more output tokens than ordinary prose of the same
length; actual usage may exceed the reservation
- For the same text, instructions or tags that slow delivery (such as
`[very slowly]`) can substantially increase output tokens. Adjusting
`speech_rate` and inserting SSML pauses do not increase output tokens
**Task result (when `status` is `completed`):**
| Field | Description |
|---|---|
| `results[0]` | Audio URL |
| `result_data[0].audio_url` | Audio URL, identical to `results[0]` |
| `result_data[0].format` | Audio format |
| `result_data[0].sample_rate` | Sample rate (Hz) |
| `usage.input_tokens` / `usage.output_tokens` / `usage.total_tokens` |
Token usage for this synthesis |
| `usage.credits_used` | Actual credits used |
operationId: createQwenAudio31TtsFlash
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/QwenAudioTtsRequest'
examples:
basic:
summary: Minimal request (default voice)
value:
model: qwen-audio-3.1-tts-flash
prompt: 我家的后面有一个很大的花园。
aliases:
summary: Text and format aliases
value:
model: qwen-audio-3.1-tts-flash
input: 我家的后面有一个很大的花园。
format: mp3
with_voice:
summary: Select a voice and output format
value:
model: qwen-audio-3.1-tts-flash
prompt: 各位听众朋友，大家好，欢迎收听晚间新闻。
voice: xuyanchu_v3.1
response_format: wav
sample_rate: 48000
expressive:
summary: Instructions and emotion tags
value:
model: qwen-audio-3.1-tts-flash
prompt: '[excited]今天的天气真不错！[laughing]我们一起出去玩吧！'
voice: longanhuan_v3.1
instruction: 用欢快、热情的语气说
english:
summary: English voice
value:
model: qwen-audio-3.1-tts-flash
prompt: Hello, this is 110. Please leave a message after the tone.
voice: Emily_v3.1
language: en
speech_rate: 0.9
ssml:
summary: SSML pauses
value:
model: qwen-audio-3.1-tts-flash
prompt: 欢迎收听今天的节目。我们马上开始。
enable_ssml: true
full_params:
summary: Full parameters
value:
model: qwen-audio-3.1-tts-flash
prompt: 今天的天气真不错，适合出去走走。
voice: yuxiaoyun_v3.1
response_format: mp3
sample_rate: 24000
volume: 60
speech_rate: 1.1
pitch: 1
instruction: 语气轻松自然，像在和朋友聊天
language: zh
enable_ssml: false
hot_fix:
pronunciation:
- 天气: tian1 qi4
replace:
- 走走: 走一走
enable_aigc_tag: false
callback_url: https://your-domain.com/webhooks/tts-completed
responses:
'200':
description: Speech synthesis task created successfully
content:
application/json:
schema:
$ref: '#/components/schemas/QwenAudioTtsResponse'
'400':
description: Invalid request parameters
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
missing_prompt:
summary: Missing prompt
value:
error:
code: missing_prompt
message: prompt is required for qwen-audio-3.1-tts-flash
type: invalid_request_error
prompt_too_long:
summary: prompt exceeds 5000 characters
value:
error:
code: prompt_too_long
message: prompt must be at most 5000 characters, got 5210
type: invalid_request_error
prompt_too_long_after_replace:
summary: Text exceeds 5000 characters after hot_fix.replace
value:
error:
code: prompt_too_long
message: >-
prompt must be at most 5000 characters after
hot_fix.replace is applied, got 5120
type: invalid_request_error
hot_fix_too_many_entries:
summary: hot_fix exceeds 200 entries
value:
error:
code: invalid_parameter
message: >-
hot_fix may contain at most 200 entries in total, got
201
type: invalid_request_error
invalid_voice:
summary: Voice is not in the supported list
value:
error:
code: invalid_voice
message: >-
voice "longanhuan" is not available for
qwen-audio-3.1-tts-flash; use a system voice from the
voice list or a voice you created with voice-enrollment
type: invalid_request_error
instruction_too_long:
summary: instruction exceeds 100 billing characters
value:
error:
code: instruction_too_long
message: >-
instruction must be at most 100 billing characters (CJK
characters count as 2), got 124
type: invalid_request_error
wrong_parameter_name:
summary: Incorrect parameter name (instructions)
value:
error:
code: unsupported_parameter
message: instructions is not supported; use "instruction"
type: invalid_request_error
unsupported_parameter:
summary: Unsupported parameter supplied
value:
error:
code: unsupported_parameter
message: seed is not supported for qwen-audio-3.1-tts-flash
type: invalid_request_error
opus_sample_rate:
summary: Unsupported sample rate for opus
value:
error:
code: invalid_parameter
message: >-
sample_rate 44100 is not supported with
response_format=opus; use one of: 8000, 12000, 16000,
24000, 48000
type: invalid_request_error
'401':
description: Unauthenticated, invalid or expired token
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: unauthorized
message: Invalid or expired token
type: authentication_error
'402':
description: Insufficient quota; top up required
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: insufficient_quota
message: Insufficient quota. Please top up your account.
type: insufficient_quota
'403':
description: Access denied
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: model_access_denied
message: >-
Token does not have access to model:
qwen-audio-3.1-tts-flash
type: invalid_request_error
'404':
description: Voice does not exist or has expired
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
examples:
voice_not_found:
summary: Voice does not exist or belongs to another account
value:
error:
code: voice_not_found
message: >-
voice
"qwen-audio-3.1-tts-flash-myvoice-5996beec833d41f4982158347ba97fae"
not found
type: invalid_request_error
voice_expired:
summary: Custom voice has expired; create a new one
value:
error:
code: voice_expired
message: >-
voice
"qwen-audio-3.1-tts-flash-myvoice-5996beec833d41f4982158347ba97fae"
has expired; create a new one with voice-enrollment
type: invalid_request_error
'429':
description: Rate limit exceeded
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: rate_limit_exceeded
message: Too many requests, please try again later
type: rate_limit_error
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: internal_error
message: Internal server error
type: api_error
components:
schemas:
QwenAudioTtsRequest:
type: object
required:
- model
description: >-
Provide at least one non-empty text field, `prompt` or `input`; if both
are supplied, their contents must match. If both `response_format` and
`format` are supplied, their values must match.
anyOf:
- required:
- prompt
properties:
prompt:
pattern: \S
- required:
- input
properties:
input:
pattern: \S
properties:
model:
type: string
description: Model name
enum:
- qwen-audio-3.1-tts-flash
default: qwen-audio-3.1-tts-flash
example: qwen-audio-3.1-tts-flash
prompt:
type: string
description: >-
Text to synthesize
**Constraints:**
- Maximum `5000` characters
- Keep punctuation in long text: long continuous passages without
sentence breaks may be truncated upstream at about `1500` output
tokens (about 120 seconds of audio). The task still reports success
and is billed for the tokens actually generated; the gateway cannot
detect this truncation
- You can also use `input`. At least one non-empty text field is
required; supplying just one is recommended. Different contents in
both fields return `400` (`parameter_conflict`)
- Text must be in a language supported by the selected voice;
otherwise pronunciation may be incorrect
**Emotion and paralinguistic tags:** Embed tags directly in the text
without extra parameters; tag text counts toward billing characters
- **Control tags**: Set the emotion or style of the following text
until the next control tag. `[sad]` sad, `[amazed]` amazed, `[deep
and loud shouting]` deep, loud shouting, `[trembling]` trembling,
`[angry]` angry, `[excited]` excited, `[sarcastic]` sarcastic,
`[curious]` curious, `[like dracula]` low and eerie, `[bored]`
bored, `[tired]` tired, `[scornful]` scornful, `[shouting]`
shouting, `[asmr]` soft ASMR whispers, `[panicked]` panicked,
`[mischievously]` mischievous, `[empathetic]` empathetic,
`[whispers]` whispering, `[reluctantly]` reluctant, `[crying]`
crying, `[serious]` serious, `[very slowly]` very slowly, `[very
fast]` very fast
- **Paralinguistic tags**: Insert a vocal effect at this position
without changing the emotion of the surrounding text. `[gasp]` gasp,
`[sighing]` sigh, `[clears throat]` clear the throat, `[giggles]`
giggle, `[laughing]` laugh, `[cough]` cough, `[snorts]` snort
**Example:** `[excited]今天的天气真不错！[laughing]我们一起出去玩吧！`
When `enable_ssml` is `true`, this field is parsed as SSML
maxLength: 5000
example: 我家的后面有一个很大的花园。
input:
type: string
description: >-
Alias for `prompt`, with the same length limits and usage rules
- Provide at least one non-empty text field, `prompt` or `input`
- If both are supplied, their contents must match; otherwise `400`
(`parameter_conflict`) is returned
maxLength: 5000
example: 我家的后面有一个很大的花园。
voice:
type: string
description: >-
Voice name, case-sensitive
- 68 system voices; see the [voice
list](/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash-voices)
for names, gender, and use cases
- Defaults to `longanhuan_v3.1` if omitted
- You can also supply a voice you created with [Voice
Enrollment](/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment):
cloned voices follow
`qwen-audio-3.1-tts-flash-{prefix}-{32-character-id}`, and designed
voices follow
`qwen-audio-3.1-tts-flash-vd-{prefix}-{32-character-id}`. Only the
account that created the voice can use it. Voices from other models,
such as `qwen-tts-vd-…` from `qwen-voice-design`, return `400`
(`invalid_voice`). Missing voices or voices owned by another account
return `404` (`voice_not_found`)
- Custom voices expire by default `6 hours` after the creation task
completes; synthesis after expiry returns `404` (`voice_expired`).
Create a new voice with Voice Enrollment
default: longanhuan_v3.1
example: longanhuan_v3.1
response_format:
type: string
description: >-
Output audio format: `mp3`, `wav`, or `opus`; defaults to `mp3`
- `opus` uses an Ogg Opus container
- You can also use `format`. Supplying just one field is
recommended; conflicting values return `400` (`parameter_conflict`)
enum:
- mp3
- wav
- opus
default: mp3
example: mp3
format:
type: string
description: >-
Alias for `response_format`; supports `mp3`, `wav`, and `opus`
- Defaults to `mp3` when neither field is supplied
- If both fields are supplied, their values must match; otherwise
`400` (`parameter_conflict`) is returned
enum:
- mp3
- wav
- opus
example: mp3
sample_rate:
type:
- integer
- 'null'
description: >-
Output sample rate (Hz)
- `22050` and `44100` are not supported when `response_format` is
`opus`
- Omitted or `null` uses the default; `0` or a value outside the
list returns `400`
enum:
- 8000
- 12000
- 16000
- 22050
- 24000
- 44100
- 48000
- null
default: 24000
example: 24000
volume:
type: integer
description: Volume, from `0` to `100`
minimum: 0
maximum: 100
default: 50
example: 50
speech_rate:
type: number
description: >-
Speech rate multiplier
- `1.0`: normal speed (default)
- `2.0`: double speed; `0.5`: half speed
Range: `0.5` to `2.0`. Adjusting speech rate does not change output
token count
minimum: 0.5
maximum: 2
default: 1
example: 1
pitch:
type: number
description: >-
Pitch multiplier
- `1.0`: default pitch
- Above `1.0` raises pitch; below `1.0` lowers it
Range: `0.5` to `2.0`
**Changing pitch also changes speech rate and audio duration**
- Higher pitch speeds up speech and shortens audio; lower pitch
slows it down and lengthens audio. Duration varies approximately
inversely with the square of the pitch value
- For a sentence lasting about 2.8 seconds at `1.0`: `0.8` is about
4.3 seconds, `1.2` about 2.1 seconds, `0.5` about 10.9 seconds, and
`2.0` about 0.7 seconds
- Small adjustments between `0.8` and `1.2` are recommended; values
near `0.5` or `2.0` make speech noticeably too slow or too fast
- If `speech_rate` is also supplied with a value other than `1.0`,
`pitch` has no effect; the two cannot be combined
- Adjusting pitch does not change output token count
minimum: 0.5
maximum: 2
default: 1
example: 1
instruction:
type: string
description: >-
Natural-language instructions to control emotion, tone, character,
dialect, and other delivery choices
**Constraints:**
- Maximum `100` billing characters: Han characters (including
Japanese kanji and Korean hanja) count as 2; other characters count
as 1, including kana and Hangul (about 50 Han characters or 100
English characters). Exceeding the limit returns `400`
**Examples:**
- `用欢快、热情的语气说` (speak cheerfully and enthusiastically)
- `请用上海话表达` (use Shanghainese; multilingual and dialect voices)
- `Speak slowly in a calm and gentle tone`
Instructions do not count toward input tokens, but can change the
generated audio duration and therefore output tokens
> The parameter is `instruction` (singular); `instructions` returns
`400`
example: 用欢快、热情的语气说
language:
type: string
description: >-
Target-language hint to improve the reading of numbers,
abbreviations, and symbols, and synthesis in less common languages
For example, with `zh`, `110` in `hello, this is 110` is read as
“yao yao ling” in Chinese
| Value | Language | Value | Language |
|---|---|---|---|
| `zh` | Chinese | `th` | Thai |
| `en` | English | `id` | Indonesian |
| `fr` | French | `vi` | Vietnamese |
| `de` | German | `es` | Spanish |
| `ja` | Japanese | `it` | Italian |
| `ko` | Korean | `ms` | Malay |
| `ru` | Russian | `fil` | Filipino |
| `pt` | Portuguese | `ar` | Arabic |
The model detects the language if omitted; this parameter does not
translate text
enum:
- zh
- en
- fr
- de
- ja
- ko
- ru
- pt
- th
- id
- vi
- es
- it
- ms
- fil
- ar
example: zh
enable_ssml:
type: boolean
description: >-
Parse `prompt` as SSML
When enabled, SSML tags can be used, such as ``
for a pause:
`欢迎收听今天的节目。我们马上开始。`
Pauses inserted with SSML do not count toward output tokens
default: false
example: false
hot_fix:
type: object
description: >-
Custom pronunciation and text replacement to correct polyphonic
characters, proper names, and other pronunciations
- `pronunciation`: annotate words with pinyin (separate syllables
with spaces and mark tones with digits, such as `tian1 qi4`) to
override the default pronunciation
- `replace`: replace specified words before synthesis. Synthesis and
billing use the replaced text, which must also stay within `5000`
characters; exceeding the limit returns `400` (`prompt_too_long`)
The two lists may contain at most `200` entries in total, counted as
key-value pairs within the objects. Exceeding the limit returns
`400` (`invalid_parameter`)
Provide at least one list. Each provided list must be a non-empty
array of objects in `{"word": "value"}` form
**Example:**
```json
{
"pronunciation": [{"天气": "tian1 qi4"}],
"replace": [{"今天": "金天"}]
}
```
properties:
pronunciation:
type: array
description: >-
Custom pronunciation list; each item is an object such as
`{"word": "pinyin"}`
items:
type: object
additionalProperties:
type: string
example:
- 天气: tian1 qi4
replace:
type: array
description: >-
Text replacement list; each item is an object such as
`{"original word": "replacement text"}`
items:
type: object
additionalProperties:
type: string
example:
- 今天: 金天
enable_aigc_tag:
type: boolean
description: >-
Embed an invisible AIGC marker in generated audio (applies to `wav`
/ `mp3` / `opus`)
default: false
example: false
callback_url:
type: string
description: >-
HTTPS callback URL for the task result
**Timing:**
- Triggered when the task completes (`completed`) or fails
(`failed`); this model does not support cancellation
- Sent after billing has been confirmed
**Security requirements:**
- HTTPS only
- Private-network IPs are prohibited (127.0.0.1, 10.x.x.x,
172.16–31.x.x, 192.168.x.x, etc.)
- URL length at most `2048` characters
**Delivery:**
- Timeout: `10` seconds
- At most `3` retries after failure, with delays of `1` / `2` / `4`
seconds
- The callback body has the same format as the task query response
- A 2xx status is success; other statuses trigger retries
format: uri
example: https://your-domain.com/webhooks/tts-completed
QwenAudioTtsResponse:
type: object
properties:
created:
type: integer
description: Task creation timestamp
example: 1790000000
id:
type: string
description: Task ID
example: task-unified-1790000000-abcd1234
model:
type: string
description: Model actually used
example: qwen-audio-3.1-tts-flash
object:
type: string
enum:
- audio.generation.task
description: Specific task object type
progress:
type: integer
description: Task progress percentage (0–100)
minimum: 0
maximum: 100
example: 0
status:
type: string
description: Task status
enum:
- pending
- processing
- completed
- failed
example: pending
task_info:
$ref: '#/components/schemas/AudioTaskInfo'
description: Audio task details
type:
type: string
enum:
- audio
description: Task output type
example: audio
usage:
$ref: '#/components/schemas/AudioUsage'
description: Usage and billing information
ErrorResponse:
type: object
properties:
error:
type: object
properties:
code:
type: string
description: Error code identifier
message:
type: string
description: Error message
type:
type: string
description: Error type
AudioTaskInfo:
type: object
properties:
can_cancel:
type: boolean
description: >-
Whether the task can be canceled (this model does not support
cancellation)
example: false
estimated_time:
type: integer
description: >-
Estimated completion time in seconds; increases with text length, up
to about `90` seconds
minimum: 0
example: 3
audio_type:
type: string
description: Audio task type
example: tts
AudioUsage:
type: object
description: Usage information
properties:
credits_reserved:
type: number
description: >-
Credits reserved based on text length; settled against actual token
usage on completion, with excess refunded or shortfall charged
minimum: 0
example: 0.0144
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
## Bearer token authentication is required for all endpoints
**Get an API key:**
Visit [API Key Management](https://evolink.ai/dashboard/keys) to obtain
your API key
**Add this request header:**
```
Authorization: Bearer YOUR_API_KEY
```
````
> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Query Task Status
> Query the status, progress, and result of a Qwen Audio 3.1 TTS Flash speech synthesis task by task ID
## OpenAPI
````yaml en/api-manual/task-management/get-task-detail.json GET /v1/tasks/{task_id}
openapi: 3.1.0
info:
title: Get Task Details API
description: >-
Query the status, progress, and result information of asynchronous tasks by
task ID
license:
name: MIT
version: 1.0.0
servers:
- url: https://api.evolink.ai
description: Production environment
security:
- bearerAuth: []
tags:
- name: Task Management
description: Asynchronous task management related APIs
paths:
/v1/tasks/{task_id}:
get:
tags:
- Task Management
summary: Query Task Status
description: >-
Query the status, progress, and result information of asynchronous tasks
by task ID
operationId: getTaskDetail
parameters:
- name: task_id
in: path
required: true
schema:
type: string
description: >-
Task ID, ignore {} when querying, append the id from the async task
response body at the end of the path
example: task-unified-1756817821-4x3rx6ny
responses:
'200':
description: Task status details
content:
application/json:
schema:
$ref: '#/components/schemas/TaskDetailResponse'
examples:
completed:
summary: Completed
value:
created: 1790000000
duration: 3
id: task-unified-1790000000-abcd1234
model: qwen-audio-3.1-tts-flash
object: audio.generation.task
progress: 100
result_data:
- audio_url: https://example.com/speech.mp3
format: mp3
sample_rate: 24000
results:
- https://example.com/speech.mp3
status: completed
task_info:
can_cancel: false
type: audio
usage:
cost:
credits: 0.0043
usd: 0.0001
cny: 0.0005
credits_used: 0.0043
input_tokens: 14
output_tokens: 33
total_tokens: 47
failed:
summary: Failed (reserved credits refunded in full)
value:
created: 1790000000
duration: 2
error:
code: invalid_prompt
message: The text could not be synthesized. Please check the input text.
id: task-unified-1790000000-abcd1234
model: qwen-audio-3.1-tts-flash
object: audio.generation.task
progress: 0
status: failed
task_info:
can_cancel: false
type: audio
'401':
description: 'Unauthenticated: API key missing, invalid, expired or disabled'
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: unauthorized
message: 'Invalid API key (request id: 20260908103000123456789abcdef)'
param: null
type: authentication_error
'403':
description: Account disabled
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: user_disabled
message: >-
Your account has been disabled (request id:
20260908103000123456789abcdef)
param: null
type: invalid_request_error
'404':
description: >-
Task does not exist or does not belong to the current API key (also
returned for malformed task IDs)
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
message: Task not found
type: invalid_request_error
param: ''
code: task_not_found
'429':
description: Request rate limit exceeded (Retry-After header is also set)
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
code: rate_limit_exceeded
message: >-
You have reached the request limit: max 60 requests per 1
minutes. Retry after 30 seconds. (request id:
20260908103000123456789abcdef)
param: null
retry_after: 30
retryable: true
type: rate_limit_error
'500':
description: Internal server error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
example:
error:
message: Failed to get task status
type: api_error
param: ''
code: internal_error
components:
schemas:
TaskDetailResponse:
type: object
properties:
created:
type: integer
description: Task creation timestamp
example: 1790000000
id:
type: string
description: Task ID
example: task-unified-1790000000-abcd1234
model:
type: string
description: Model used
example: qwen-audio-3.1-tts-flash
object:
type: string
description: Task object type
enum:
- audio.generation.task
example: audio.generation.task
progress:
type: integer
minimum: 0
maximum: 100
description: Task progress percentage
example: 100
status:
type: string
description: >-
Task status. Note: while the task is still pending upstream the
query API already reports "processing", so clients normally only see
processing / completed / failed.
enum:
- pending
- processing
- completed
- failed
example: completed
type:
type: string
description: Task output type
enum:
- audio
example: audio
duration:
type: integer
description: >-
Task duration in seconds. Only present when status is "completed" or
"failed".
example: 3
results:
type: array
items:
type: string
format: uri
description: >-
Audio URL list with one item, valid for 24 hours. Only present when
status is "completed".
example:
- https://example.com/speech.mp3
result_data:
type: array
description: >-
Result details with one item. Only present when status is
"completed".
items:
type: object
properties:
audio_url:
type: string
format: uri
description: Audio URL, identical to results[0]
example: https://example.com/speech.mp3
format:
type: string
description: Audio format
enum:
- mp3
- wav
- opus
example: mp3
sample_rate:
type: integer
description: Sample rate (Hz)
example: 24000
usage:
type: object
description: >-
Usage and billing information. Only present when status is
"completed".
properties:
credits_used:
type: number
description: >-
Credits actually charged for this task. Omitted only if billing
could not be settled yet.
example: 0.0043
cost:
type: object
description: >-
Cost of this task expressed in three currencies, converted from
credits_used (values are rounded up).
properties:
credits:
type: number
description: Credits charged (same as credits_used)
example: 0.0043
usd:
type: number
description: Equivalent amount in USD
example: 0.0001
cny:
type: number
description: Equivalent amount in CNY
example: 0.0005
input_tokens:
type: integer
description: Input tokens actually used (related to text length)
example: 14
output_tokens:
type: integer
description: >-
Output tokens actually used (related to generated audio
duration)
example: 33
total_tokens:
type: integer
description: input_tokens + output_tokens
example: 47
error:
type: object
nullable: true
description: >-
Error information when the task fails (only present when status is
"failed"). Note: error.code here is a string-type business error
code, different from HTTP status codes. Failed tasks are refunded in
full.
properties:
code:
type: string
description: Business error code (string type)
example: invalid_prompt
message:
type: string
description: User-friendly error description with troubleshooting tips
example: The text could not be synthesized. Please check the input text.
details:
type: string
description: Additional error details, present only when available
task_info:
type: object
description: Task detailed information
properties:
can_cancel:
type: boolean
description: >-
Whether the task can be cancelled. Always false: this model does
not support cancellation
example: false
ErrorResponse:
type: object
properties:
error:
type: object
properties:
code:
type: string
description: Error code (string type)
example: task_not_found
message:
type: string
description: >-
Error description message. Errors raised by middleware (401,
429) are suffixed with " (request id: ...)"
example: Task not found
type:
type: string
description: Error type
example: invalid_request_error
param:
type: string
nullable: true
description: Related parameter name; null or empty for this endpoint
retry_after:
type: integer
description: Seconds to wait before retrying (429 only)
example: 30
retryable:
type: boolean
description: Whether the request can be retried (429 only)
example: true
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: >-
##All APIs require Bearer Token authentication##
**Get API Key:**
Visit [API Key Management Page](https://evolink.ai/dashboard/keys) to
get your API Key
**Add to request header:**
```
Authorization: Bearer YOUR_API_KEY
```
````
> ## Documentation Index
> Fetch the complete documentation index at: https://evolink.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Qwen Audio 3.1 TTS Flash Voices
> IDs, gender, languages, and usage examples for 68 system voices, plus custom voice instructions.
Qwen Audio 3.1 TTS Flash selects a voice with the `voice` parameter in the [speech synthesis API](/docs/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash). There are **68** system voices, ready to use without creating a voice first.
* `voice` is **case-sensitive**; copy its value exactly as shown below
* If `voice` is omitted, the default is `longanhuan_v3.1`
* Use the table’s `voice` column in requests; names, gender, voice qualities, and use cases help you choose a voice
* The text must be in a language supported by the selected voice; otherwise pronunciation may be incorrect or speech unnatural
## Usage Examples
Send the following request body to `POST /v1/audios/generations`, replacing `voice` with the desired voice ID. See the [speech synthesis API](/docs/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash) for all parameters and task queries.
```json Chinese voice theme={null}
{
"model": "qwen-audio-3.1-tts-flash",
"prompt": "欢迎使用语音合成，让文字变成自然流畅的声音。",
"voice": "longanhuan_v3.1"
}
```
```json English voice theme={null}
{
"model": "qwen-audio-3.1-tts-flash",
"prompt": "Welcome to our audio guide. Let us turn your words into speech.",
"voice": "Emily_v3.1",
"language": "en"
}
```
All voices can use `instruction` and inline emotion tags, such as `[excited]` and `[laughing]`, to control emotion and tone. See the `prompt` and `instruction` descriptions in the [speech synthesis API](/docs/en/api-manual/audio-series/qwen-audio-tts/qwen-audio-3.1-tts-flash).
## Multilingual and Dialect Voices
**4** voices. Each supports all the dialects and languages below:
* **Dialects**: Shanghainese, Cantonese, Northeastern Chinese, Chongqing, Shaanxi, Yunnan, Ningbo, and Gansu dialects
* **Languages**: Japanese, Korean, French, German, Portuguese, Italian, Vietnamese, and Indonesian
For dialect synthesis, specify the dialect in `instruction`, for example `请用上海话表达` (use Shanghainese).
| Name | voice | Gender | Language |
| - | - | - | - |
| Long Anhuan (default) | `longanhuan_v3.1` | Female | Mandarin, dialects and multiple languages |
| Long Anlingxin | `longanlingxin_v3.1` | Female | Mandarin, dialects and multiple languages |
| Long Anfengyue | `longanfengyue_v3.1` | Female | Mandarin, dialects and multiple languages |
| Xu Nanchuan | `xunanchuan_v3.1` | Male | Mandarin, dialects and multiple languages |
## Premium Chinese Voices
**22** voices, supporting Mandarin Chinese only.
| Name | voice | Gender | Voice qualities | Use cases |
| - | - | - | - | - |
| Yu Xiaoyun | `yuxiaoyun_v3.1` | Female | energetic, friendly, natural | advertising and marketing, broadcasting, customer service assistant, narration |
| Qiao Xiaojiao | `qiaoxiaojiao_v3.1` | Female | charming, cute | advertising and marketing, customer service assistant, audiobooks |
| Xia Xiaochen | `xiaxiaochen_v3.1` | Female | energetic, bright | advertising and marketing, audiobooks |
| An Mingyuan | `anmingyuan_v3.1` | Male | clear, natural | advertising and marketing, audiobooks, narration |
| Wen Huaiqing | `wenhuaiqing_v3.1` | Female | clear, soft | children’s stories, customer service assistant, advertising and marketing, news reading |
| An Xiaolan | `anxiaolan_v3.1` | Female | sweet and clear, pure | audiobooks, customer service assistant, narration, news reading, advertising and marketing |
| Xie Shurou | `xieshurou_v3.1` | Female | soft, natural, articulate | audiobooks, customer service assistant, narration |
| Bai Qinglan | `baiqinglan_v3.1` | Female | bright, innocent | voice assistant, customer service assistant |
| Xu Yuyuan | `xuyuyuan_v3.1` | Female | articulate, mature, textured | advertising and marketing, news reading, narration, customer service assistant, audiobooks |
| An Ruorou | `anruorou_v3.1` | Female | breathy, articulate | narration, voice assistant |
| Wen Huaizhi | `wenhuaizhi_v3.1` | Female | steady, mature | audiobooks, news reading, advertising and marketing, customer service assistant, narration |
| Xiao Xingzhi | `xiaoxingzhi_v3.1` | Female | dignified, regal | news reading, audiobooks, narration, customer service assistant |
| Gu Yunshu | `guyunshu_v3.1` | Female | mature, steady | music radio, customer service assistant, audiobooks, narration |
| Huo Zhuoshi | `huozhuoshi_v3.1` | Male | clear | audiobooks, advertising and marketing, narration |
| Ye Qinghe | `yeqinghe_v3.1` | Female | friendly, gentle | audiobooks, advertising and marketing, narration, customer service assistant |
| Yun Huanhuan | `yunhuanhuan_v3.1` | Female | high-pitched, enthusiastic | audiobooks, narration, customer service assistant |
| Xu Xiaoqiao | `xuxiaoqiao_v3.1` | Female | natural, playful | audiobooks, narration, customer service assistant |
| Bai Anran | `baianran_v3.1` | Female | low-pitched, rich, breathy | dubbing and explanations, audiobooks, narration |
| Xu Yanchu | `xuyanchu_v3.1` | Female | composed, resonant | news reading, audiobooks |
| Ye Zhiqing | `yezhiqing_v3.1` | Female | lively, natural | children’s stories, customer service assistant, voice assistant |
| Andi | `andi_v3.1` | Male | American-born Chinese accent | voice assistant |
| An Yuqing | `anyuqing_v3.1` | Female | sweet young woman | voice assistant, narration, news reading |
## Premium English Voices
**15** voices, supporting English only.
| Name | voice | Gender | Accent |
| - | - | - | - |
| Emily | `Emily_v3.1` | Female | British |
| Luna | `Luna_v3.1` | Female | British |
| Eric | `Eric_v3.1` | Male | British |
| Luca | `Luca_v3.1` | Male | British |
| Abby | `Abby_v3.1` | Female | American |
| Annie | `Annie_v3.1` | Female | American |
| Ava | `Ava_v3.1` | Female | American |
| Beth | `Beth_v3.1` | Female | American |
| Betty | `Betty_v3.1` | Female | American |
| Cally | `Cally_v3.1` | Female | American |
| Cindy | `Cindy_v3.1` | Female | American |
| Donna | `Donna_v3.1` | Female | American |
| Andy | `Andy_v3.1` | Male | American |
| Brian | `Brian_v3.1` | Male | American |
| David | `David_v3.1` | Male | American |
## Other System Voices
**27** voices. Supported languages are not listed individually for this group; use text in your target language to check the synthesis quality.
| Name | voice | Gender | Voice qualities | Use cases |
| - | - | - | - | - |
| Long Anyuanfei | `longanyuanfei_v3.1` | Female | proud imperial consort | social companionship |
| Long Jielidou | `longjielidou_v3.1` | Male | innocent boy | children’s companionship |
| Long Anlingxi | `longanlingxi_v3.1` | Female | cute and sweet | social companionship |
| Long Huohuo | `longhuohuo_v3.1` | Male | mischievous teenage boy | character voice |
| Long Yingtao | `longyingtao_v3.1` | Female | gentle, calm woman | customer service |
| Long Anya | `longanya_v3.1` | Female | refined, elegant woman | social companionship |
| Long Wan | `longwan_v3.1` | Female | delicate, soft-spoken woman | social companionship |
| Long Xing | `longxing_v3.1` | Female | gentle girl next door | social companionship |
| Long Hua | `longhua_v3.1` | Female | energetic, sweet woman | social companionship |
| Long Han | `longhan_v3.1` | Male | warm, devoted man | social companionship |
| Long Anzhi | `longanzhi_v3.1` | Male | wise, moderately mature man | social companionship |
| Long Zhe | `longzhe_v3.1` | Male | awkward but warm man | social companionship |
| Long Anyang | `longanyang_v3.1` | Male | cheerful young man | social companionship |
| Li Bai | `libai_v3.1` | Male | classical poet | poetry recitation |
| Long Ling | `longling_v3.1` | Female | childlike, reserved girl | child voice |
| Long Niuniu | `longniuniu_v3.1` | Male | cheerful boy | children’s audiobooks |
| Long Shanshan | `longshanshan_v3.1` | Male | theatrical child voice | children’s audiobooks |
| Long Paopao | `longpaopao_v3.1` | Female | Powerpuff-style voice | children’s companionship |
| loongstella | `loongstella_v3.1` | Female | confident, brisk woman | news reading |
| Long Yuan | `longyuan_v3.1` | Female | warm, soothing woman | audiobooks |
| Long Miao | `longmiao_v3.1` | Female | expressive female intonation | audiobooks |
| Long Sanshu | `longsanshu_v3.1` | Male | composed, textured male voice | audiobooks |
| Long Anli | `longanli_v3.1` | Female | brisk, poised woman | voice assistant |
| Long Anwen | `longanwen_v3.1` | Female | elegant, articulate woman | voice assistant |
| Long Anlang | `longanlang_v3.1` | Male | clear, brisk man | voice assistant |
| Long Xiaoxia | `longxiaoxia_v3.1` | Female | composed, authoritative woman | voice assistant |
| Long Anchong | `longanchong_v3.1` | Male | enthusiastic salesman | live shopping |
## Custom Voices
For your own voice, use [Voice Enrollment](/docs/en/api-manual/audio-series/qwen-audio-tts/voice-enrollment): provide a recording to clone a voice, or a text description to design one. After the task completes, pass the full returned `voice` name to the speech synthesis API.
* Custom voices can only be used by the account that created them
* By default, they expire **6 hours** after the creation task completes; synthesis calls do not extend their lifetime
* After expiry, synthesis returns `404` (`voice_expired`); create a new voice with Voice Enrollment
* Voices created with the old `qwen-voice-design` model cannot be used here; recreate them with Voice Enrollment when migrating