API reference

Updated at:

Speech File Transcriber Lite converts recorded audio files into text. Submit an HTTP or HTTPS URL from which the service can download the file, and retrieve the transcription asynchronously. Direct submission of local files is not supported. Unlike standard file transcription, the Lite service returns results within 24 hours.

Prerequisites and billing

For billing rules, see Billable items. For information about the commercial edition, see Billing methods.

Limits

Item

Requirement

File formats

Mono and stereo WAV, MP3, MP4, M4A, WMA, AAC, OGG, AMR, and FLAC files are supported.

File size and duration

Audio files must not exceed 512 MB, video files must not exceed 2 GB, and the total file duration must not exceed 12 hours.

File access

The service must be able to download the file from the URL. Use a domain name, not an IP address or local file path. URLs must not contain spaces; avoid Chinese characters where possible. The HTTP Content-Length response header must match the actual response body length.

Result availability

Tasks complete within 24 hours. Results are retained on the server for 72 hours.

Concurrency and QPS

There is no limit on concurrent tasks. The per-user QPS limits are 200 for submission and 500 for queries. Queries for the same TaskId are limited to 1 QPS.

Intelligent speaker separation

Supported only for mono audio at 8 kHz or 16 kHz.

Important

The standard 24-hour turnaround does not apply to large submissions of more than 500 hours of audio within half an hour. Contact a presales specialist for such workloads.

For details about quotas, see Concurrency and QPS.

Custom language models and hotwords are supported. For instructions, see Custom language model and Use the POP API to manage business-specific hotwords.

Steps

  1. Configure a recognition model for the project based on the audio sample rate, language, and use case. Select language and dialect models in the project configuration, not in individual recognition requests.

  2. Store the audio file in OSS or on your own file server and obtain a downloadable URL. For a private OSS object, use a presigned URL with an expiration time; the object does not need public-read access. For instructions, see Use presigned URLs to download or preview objects.

  3. Call SubmitTask with the file URL and Appkey to obtain a TaskId.

  4. Call GetTaskResult to query the task status and result, or specify a callback URL when submitting the task to receive the result after completion.

OSS files in the same region can be accessed over the internal network without Internet traffic fees. For configuration instructions, see Configure an OSS internal URL for file transcription.

Interaction flow

After submitting a task, the client obtains its result by polling or callback. The TaskId in the JSON response body associates the submission with subsequent result queries.

image

API information

The service provides RPC-style POP APIs authenticated with AccessKey signatures. The API version is 2021-12-21.

Region

regionId / endpointName

Endpoint

China (Shanghai)

cn-shanghai

speechfiletranscriberlite.cn-shanghai.aliyuncs.com

China (Beijing)

cn-beijing

speechfiletranscriberlite.cn-beijing.aliyuncs.com

China (Shenzhen)

cn-shenzhen

speechfiletranscriberlite.cn-shenzhen.aliyuncs.com

Action

HTTP method

Purpose

SubmitTask

POST

Submits a transcription task. The Task parameter is a JSON string containing the task parameters described below.

GetTaskResult

GET

Queries the task status and result by TaskId.

Submit a transcription task

Request parameters

Serialize the task parameters as a JSON string and pass it as the Task parameter of SubmitTask. The following example shows the task parameters. The optional valid_times parameter restricts recognition to specified time intervals.

Download the English sample audio and upload it to a location that the service can access over HTTP or HTTPS. Replace file_link with the file URL.

{
  "appkey": "your-appkey",
  "file_link": "https://your-domain.example/nls-sample-en-16k.wav",
  "auto_split": false,
  "enable_words": false,
  "enable_sample_rate_adaptive": true,
  "valid_times": [
    {
      "begin_time": 0,
      "end_time": 3049,
      "channel_id": 0
    }
  ]
}

Parameter

Type

Required

Description

appkey

String

Yes

The Appkey of the project.

file_link

String

Yes

The downloadable audio file URL. The project model must support the sample rate and audio use case.

version

String

No

The recognition version. Set to 4.0 to use disfluency removal. This is different from the POP API version.

enable_words

Boolean

No

Specifies whether to return word information. Default: false.

enable_sample_rate_adaptive

Boolean

No

Specifies whether to downsample audio above 16 kHz to 16 kHz. Default: false.

enable_callback

Boolean

No

Specifies whether to enable callbacks. Default: false.

callback_url

String

Conditional

The callback URL. Required when enable_callback=true. HTTP and HTTPS are supported. The host must not be an IP address. The URL must accept POST requests.

speaker_num

Integer

No

Helps specify the number of speakers, from 2 to 100. The default is 2 for 8 kHz and 100 for 16 kHz. Use with auto_split and supervise_type. This guides the algorithm but does not guarantee the final speaker count.

auto_split

Boolean

No

Specifies whether to enable intelligent speaker separation. In a two-party conversation, use each sentence's ChannelId to distinguish speakers. The first speaker usually has ChannelId 0. For 8 kHz stereo audio, the two channels distinguish the two parties; channel0 and channel1 identify the audio tracks.

supervise_type

Integer

No

Specifies how the speaker count is determined. Use with auto_split and speaker_num. If omitted, the caller specifies the count for 8 kHz audio and the algorithm determines it for 16 kHz audio. 1: use speaker_num. 2: let the algorithm determine the count.

enable_inverse_text_normalization

Boolean

No

Specifies whether to enable inverse text normalization (ITN), which converts Chinese numbers to Arabic numerals. Default: false.

enable_disfluency

Boolean

No

Specifies whether to remove filler words. Default: false. Requires version to be 4.0 when enabled.

enable_punctuation_prediction

Boolean

No

Specifies whether to add punctuation. Default: true.

valid_times

List of ValidTime

No

The valid recognition intervals, which exclude unwanted portions of the audio. See the field descriptions below.

max_end_silence

Integer

No

The maximum end-of-sentence silence in milliseconds. Range: 200–6000. Default: 800. Ignored when enable_semantic_sentence_detection is enabled.

max_single_segment_time

Integer

No

The maximum sentence duration in milliseconds. Minimum: 5000. Default: 60000. Ignored when enable_semantic_sentence_detection is enabled.

customization_id

String

No

The ID of a custom model created through the POP API. Omitted by default.

class_vocabulary_id

String

No

The ID of a class-based hotword list. Omitted by default.

vocabulary_id

String

No

The ID of a general hotword list. Omitted by default.

enable_semantic_sentence_detection

Boolean

No

Specifies whether to enable semantic sentence segmentation. Default: false.

enable_timestamp_alignment

Boolean

No

Specifies whether to enable timestamp alignment. Default: false.

first_channel_only

Boolean

No

Specifies whether to recognize only the first channel. If omitted, both channels are processed for 8 kHz audio and one channel for 16 kHz audio. false: process both channels at either sample rate. true: process one channel at either sample rate. Enable this option if identical content in both channels causes duplicate results.

special_word_filter

String (JSON string)

No

The sensitive-word configuration. By default, the original text is retained. Words can be removed or replaced with *, and the default sensitive-word list can be enabled. See the configuration example below.

punctuation_mark

String

No

Additional punctuation for sentence segmentation. By default, periods, question marks, and exclamation marks are used. Multiple punctuation marks are allowed without spaces; Chinese and English punctuation are distinguished. Non-punctuation characters have no effect. For example, , adds the English comma, and ,, adds both Chinese and English commas.

sentence_max_length

Integer

No

The maximum number of displayed characters per sentence, from 4 to 50. Disabled by default. If enabled without a character count, long sentences are segmented. Use this parameter to control subtitle line length.

Important

For 8 kHz stereo audio, billing is based on the audio duration as for mono audio. For 16 kHz stereo audio, billing is based on the number of channels multiplied by the audio duration.

ValidTime fields

Parameter

Type

Required

Description

begin_time

Int

Yes

The start offset of the interval from the beginning of the file, in milliseconds.

end_time

Int

Yes

The end offset of the interval from the beginning of the file, in milliseconds.

channel_id

Int

Yes

The zero-based audio track index for the interval.

Custom word filtering

Set special_word_filter to a JSON string with the following structure. system_reserved_filter enables the default sensitive-word list. filter_with_empty removes the specified words, and filter_with_signed replaces them with *. You can specify all or some of these settings. This example removes “monday” and masks “weather” in the recognition result.

{
  "system_reserved_filter": true,
  "filter_with_empty": {
    "word_list": [
      "monday"
    ]
  },
  "filter_with_signed": {
    "word_list": [
      "weather"
    ]
  }
}

The default list is available in the Chinese sensitive-word list.

Submission response

{
  "TaskId": "4b56f0c4b7e611e88f34c33c2a60****",
  "RequestId": "E4B183CC-6CFE-411E-A547-D877F7BD****",
  "StatusText": "SUCCESS",
  "StatusCode": 21050000
}

Field

Type

Description

TaskId

String

The task ID returned after successful submission. Use it to query results.

RequestId

String

The request ID for troubleshooting.

StatusCode

Int

The business status code. 21050000 indicates successful submission, not completion of recognition.

StatusText

String

The business status message.

Obtain transcription results

A successful HTTP request does not necessarily mean that transcription succeeded. Check StatusCode and StatusText. Continue waiting while the task is queued or running, read the result after completion, and handle failures based on the error code.

Result delivery methods

Polling

Call GetTaskResult with the TaskId returned by the submission API as a query parameter. Space out queries to stay within the limits of 500 QPS per user and 1 QPS per TaskId.

Parameter

Type

Required

Description

TaskId

String

Yes

The task ID returned after submission.

Callback

Set enable_callback=true and callback_url when submitting the task. After completion, the service posts the result to the callback URL. The URL must use HTTP or HTTPS with a domain name rather than an IP address, and must accept POST requests.

The callback includes RequestTime, when the task was submitted, and SolveTime, when it completed. Both are Unix timestamps in milliseconds. For example, 1553062810452 corresponds to March 20, 2019, 14:20:10 (UTC+8).

{
  "Result": {
    "Sentences": [
      {
        "EndTime": 1520,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 0,
        "Text": "today is monday. ",
        "ChannelId": 0,
        "SpeechRate": 118,
        "EmotionValue": 6.1
      },
      {
        "EndTime": 3040,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 1520,
        "Text": "the weather is nice. ",
        "ChannelId": 0,
        "SpeechRate": 157,
        "EmotionValue": 6.1
      }
    ]
  },
  "TaskId": "36d01b244ad811e9952db7bb7ed2****",
  "StatusCode": 21050000,
  "StatusText": "SUCCESS",
  "RequestTime": 1553062810452,
  "SolveTime": 1553062810831,
  "BizDuration": 3049
}

Response examples

The successful responses below transcribe this English sample audio. To return word information, set enable_words=true. Both polling and callbacks can return word information.

Successful transcription

{
  "TaskId": "9e7e315f77b3404e87a5c965634c****",
  "RequestId": "01A17D2C-94BB-5CF0-B211-C0E90322****",
  "RecDuration": 3049,
  "StatusText": "SUCCESS",
  "BizDuration": 3049,
  "SolveTime": 1793101433918,
  "StatusCode": 21050000,
  "Result": {
    "Sentences": [
      {
        "EndTime": 1520,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 0,
        "Text": "today is monday. ",
        "ChannelId": 0,
        "SpeechRate": 118,
        "EmotionValue": 6.1
      },
      {
        "EndTime": 3040,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 1520,
        "Text": "the weather is nice. ",
        "ChannelId": 0,
        "SpeechRate": 157,
        "EmotionValue": 6.1
      }
    ]
  }
}

Word information

{
  "TaskId": "bc2ba382cd3547939e554cba32e2****",
  "RequestId": "01A17D2C-A149-5BEF-B678-2A5C24FB****",
  "RecDuration": 3049,
  "StatusText": "SUCCESS",
  "BizDuration": 3049,
  "SolveTime": 1793101436740,
  "StatusCode": 21050000,
  "Result": {
    "Words": [
      {
        "Word": "today ",
        "EndTime": 608,
        "BeginTime": 0,
        "ChannelId": 0
      },
      {
        "Word": "is ",
        "EndTime": 912,
        "BeginTime": 608,
        "ChannelId": 0
      },
      {
        "Word": "monday",
        "EndTime": 1520,
        "BeginTime": 912,
        "ChannelId": 0
      },
      {
        "Word": "the ",
        "EndTime": 1824,
        "BeginTime": 1520,
        "ChannelId": 0
      },
      {
        "Word": "weather ",
        "EndTime": 2432,
        "BeginTime": 1824,
        "ChannelId": 0
      },
      {
        "Word": "is ",
        "EndTime": 2736,
        "BeginTime": 2432,
        "ChannelId": 0
      },
      {
        "Word": "nice",
        "EndTime": 3040,
        "BeginTime": 2736,
        "ChannelId": 0
      }
    ],
    "Sentences": [
      {
        "EndTime": 1520,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 0,
        "Text": "today is monday. ",
        "ChannelId": 0,
        "SpeechRate": 118,
        "EmotionValue": 6.1
      },
      {
        "EndTime": 3040,
        "SilenceDuration": 0,
        "SpeakerId": "1",
        "BeginTime": 1520,
        "Text": "the weather is nice. ",
        "ChannelId": 0,
        "SpeechRate": 157,
        "EmotionValue": 6.1
      }
    ]
  }
}

Queued

{
        "TaskId": "c7274235b7e611e88f34c33c2a60****",
        "RequestId": "981AD922-0655-46B0-8C6A-5C836822****",
        "StatusText": "QUEUEING",
        "StatusCode": 21050002
}

Running

{
        "TaskId": "c7274235b7e611e88f34c33c2a60****",
        "RequestId": "8E908ED2-867F-457E-82BF-4756194A****",
        "StatusText": "RUNNING",
        "BizDuration": 0,
        "StatusCode": 21050001
}

Download failure

{
  "TaskId": "4b56f0c4b7e611e88f34c33c2a60****",
  "RequestId": "E4B183CC-6CFE-411E-A547-D877F7BD****",
  "RecDuration": 0,
  "StatusText": "FILE_DOWNLOAD_FAILED",
  "BizDuration": 0,
  "SolveTime": 0,
  "StatusCode": 41050002
}

Response fields

The returned fields vary with the task status. Do not assume that Result is present when a task is queued, running, or has failed.

Field

Type

Description

TaskId

String

The task ID.

RequestId

String

The request ID for troubleshooting.

StatusCode

Int

The business status code.

StatusText

String

The business status message, such as SUCCESS, RUNNING, or QUEUEING.

Result

Object

The transcription result object. Read it when the task succeeds and produces transcription content.

RecDuration

Long

The source audio duration, in milliseconds.

BizDuration

Long

The audio duration processed by this task, in milliseconds. It can differ from the source file duration when valid_times is specified.

SolveTime

Long

The task completion time as a Unix timestamp in milliseconds.

Result fields

Field

Type

Description

Sentences

List of SentenceResult

The sentence recognition results when StatusText=SUCCESS.

Words

List of WordResult

Word information. Requires enable_words=true.

SentenceResult fields

Field

Type

Description

ChannelId

Int

The audio track ID of the sentence.

BeginTime

Int

The sentence start offset from the beginning of the file, in milliseconds.

EndTime

Int

The sentence end offset from the beginning of the file, in milliseconds.

Text

String

The recognized text of the sentence.

SpeakerId

String

The speaker identifier.

EmotionValue

Float

The emotion energy value, calculated as the volume in decibels divided by 10. Range: 1–10. Higher values indicate stronger emotion.

SilenceDuration

Int

The silence between this sentence and the previous one, in seconds.

SpeechRate

Int

The average speech rate of the sentence, in characters per minute for Chinese or words per minute for English.

WordResult fields

Field

Type

Description

BeginTime

Int

The word start time, in milliseconds.

EndTime

Int

The word end time, in milliseconds.

ChannelId

Int

The audio track ID of the word.

Word

String

The word text.

Languages and dialects

Choose a project model for the audio sample rate and use case. The tables below list support for punctuation, ITN, disfluency removal, semantic sentence segmentation, and audio-text alignment.

Languages

Language

Model name

Sample rate

Punctuation

ITN

Disfluency detection

Semantic sentence detection

Audio and text alignment

English

General - English, Education Livestream - English, Education Content Analysis - English

16k

Supported

Supported

Supported

Not supported

Supported

Call Center (General)

8k

Supported

Supported

Supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Japanese

General - Japanese

16k

Supported

Supported

Not supported

Not supported

Supported

Spanish

General - Spanish

16k

Supported

Supported

Not supported

Not supported

Not supported

General - Spanish Call Center General

8k

Supported

Supported

Not supported

Not supported

Not supported

Arabic

General - Arabic

16k

Supported

Not supported

Not supported

Not supported

Not supported

Kazakh

General - Kazakh

16k

Supported

Not supported

Not supported

Not supported

Not supported

Korean

General - Korean

16k

Supported

Supported

Not supported

Not supported

Not supported

Thai

General - Thai

16k

Not supported

Not supported

Not supported

Not supported

Not supported

General - Thai Call Center General

8k

Not supported

Not supported

Not supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Indonesian

General - Indonesian

16k

Supported

Supported

Not supported

Not supported

Not supported

Call Center (General)

8k

Supported

Supported

Not supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Russian

General - Russian

16k

Supported

Supported

Not supported

Not supported

Not supported

Vietnamese

General - Vietnamese

16k

Supported

Supported

Not supported

Not supported

Not supported

General - Vietnamese Call Center General

8k

Supported

Supported

Not supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

French

General - French

16k

Supported

Supported

Not supported

Not supported

Not supported

German

General - German

16k

Supported

Supported

Not supported

Not supported

Not supported

Italian

General - Italian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Hindi

General - Hindi

16k

Supported

Not supported

Not supported

Not supported

Not supported

Malay

General - Malay

16k

Supported

Not supported

Not supported

Not supported

Not supported

General - Malay Call Center General

8k

Supported

Not supported

Not supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Filipino

General - Filipino

16k

Supported

Supported

Not supported

Not supported

Not supported

Call Center (General)

8k

Supported

Supported

Not supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Tamil

General - Tamil

16k

Supported

Not supported

Not supported

Not supported

Not supported

Portuguese

General - Portuguese

16k

Supported

Supported

Not supported

Not supported

Not supported

Turkish

General - Turkish

16k

Supported

Not supported

Not supported

Not supported

Not supported

Polish

General - Polish

16k

Supported

Not supported

Not supported

Not supported

Not supported

Ukrainian

General - Ukrainian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Romanian

General - Romanian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Dutch

General - Dutch

16k

Supported

Not supported

Not supported

Not supported

Not supported

Greek

General - Greek

16k

Supported

Not supported

Not supported

Not supported

Not supported

Hungarian

General - Hungarian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Javanese

General - Javanese

16k

Supported

Not supported

Not supported

Not supported

Not supported

Bengali

General - Bengali

16k

Supported

Not supported

Not supported

Not supported

Not supported

Burmese

General - Burmese

16k

Supported

Not supported

Not supported

Not supported

Not supported

Lao

General - Lao

16k

Supported

Not supported

Not supported

Not supported

Not supported

Swahili

General - Swahili

16k

Supported

Not supported

Not supported

Not supported

Not supported

Azerbaijani

General - Azerbaijani

16k

Supported

Not supported

Not supported

Not supported

Not supported

Persian

General - Persian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Sinhala

General - Sinhala

16k

Supported

Not supported

Not supported

Not supported

Not supported

Catalan

General - Catalan

16k

Supported

Not supported

Not supported

Not supported

Not supported

Khmer

General - Khmer

16k

Supported

Not supported

Not supported

Not supported

Not supported

Hebrew

General - Hebrew

16k

Supported

Not supported

Not supported

Not supported

Not supported

Croatian

General - Croatian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Hausa

General - Hausa

16k

Supported

Not supported

Not supported

Not supported

Not supported

Marathi

General - Marathi

16k

Supported

Not supported

Not supported

Not supported

Not supported

Telugu

General - Telugu

16k

Supported

Not supported

Not supported

Not supported

Not supported

Punjabi

General - Punjabi

16k

Supported

Not supported

Not supported

Not supported

Not supported

Swedish

General - Swedish

16k

Supported

Not supported

Not supported

Not supported

Not supported

Bulgarian

General - Bulgarian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Danish

General - Danish

16k

Supported

Not supported

Not supported

Not supported

Not supported

Norwegian

General - Norwegian

16k

Supported

Not supported

Not supported

Not supported

Not supported

Kannada

General - Kannada

16k

Supported

Not supported

Not supported

Not supported

Not supported

Malayalam

General - Malayalam

16k

Supported

Not supported

Not supported

Not supported

Not supported

Czech

General - Czech

16k

Supported

Not supported

Not supported

Not supported

Not supported

Urdu

General - Urdu

16k

Supported

Not supported

Not supported

Not supported

Not supported

Nepali

General - Nepali

16k

Supported

Not supported

Not supported

Not supported

Not supported

Mongolian (Outer Mongolia)

General - Mongolian (Outer Mongolia)

16k

Supported

Not supported

Not supported

Not supported

Not supported

Uzbek

General - Uzbek

16k

Supported

Not supported

Not supported

Not supported

Not supported

Dialects

Language

Model name

Sample rate

Punctuation

ITN

Disfluency detection

Semantic sentence detection

Audio and text alignment

Cantonese

General - Cantonese

16k

Supported

Supported

Supported

Not supported

Supported

Call Center (General)

8k

Supported

Supported

Supported

Not supported

Supported

Cantonese-Mandarin Code-switching

8k

Supported

Supported

Supported

Not supported

Not supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Cantonese (Traditional Chinese)

General - Cantonese (Traditional Chinese)

8k

Supported

Not supported

Not supported

Not supported

Not supported

General - Cantonese (Traditional Chinese)

16k

Supported

Not supported

Not supported

Not supported

Not supported

Sichuanese

General - Sichuanese

16k

Supported

Supported

Supported

Supported

Supported

Call Center (General)

8k

Supported

Supported

Supported

Supported

Supported

Hubei dialect

General - Hubei dialect

16k

Supported

Supported

Supported

Supported

Supported

General - Hubei dialect

8k

Supported

Supported

Supported

Supported

Supported

Shanghainese

General - Shanghainese

16k

Supported

Supported

Supported

Supported

Not supported

Hunan dialect

General - Hunan dialect

16k

Supported

Supported

Supported

Supported

Supported

Henan dialect

General - Henan dialect

16k

Supported

Supported

Supported

Supported

Supported

General - Henan dialect

8k

Supported

Supported

Supported

Supported

Supported

Zhejiang dialect

General - Zhejiang dialect

16k

Supported

Supported

Supported

Supported

Not supported

Northeastern Mandarin

General - Northeastern Mandarin

16k

Supported

Supported

Supported

Supported

Supported

Shandong dialect

General - Shandong dialect

16k

Supported

Supported

Supported

Supported

Supported

Tianjin dialect

General - Tianjin dialect

16k

Supported

Supported

Supported

Supported

Supported

Shaanxi dialect

General - Shaanxi dialect

16k

Supported

Supported

Supported

Supported

Supported

Shanxi dialect

General - Shanxi dialect

16k

Supported

Supported

Supported

Supported

Supported

Guizhou dialect

General - Guizhou dialect

16k

Supported

Supported

Supported

Supported

Supported

Yunnan dialect

General - Yunnan dialect

16k

Supported

Supported

Supported

Supported

Supported

Gansu dialect

General - Gansu dialect

16k

Supported

Supported

Supported

Supported

Supported

Suzhou dialect

General - Suzhou dialect

16k

Supported

Supported

Supported

Supported

Not supported

Minnan

General - Minnan

16k

Supported

Supported

Supported

Supported

Not supported

Jiangxi dialect

General - Jiangxi dialect

16k

Supported

Supported

Supported

Supported

Supported

Ningxia dialect

General - Ningxia dialect

16k

Supported

Supported

Supported

Supported

Supported

Guangxi dialect

General - Guangxi dialect

16k

Supported

Supported

Supported

Supported

Supported

General - Guangxi dialect

8k

Supported

Supported

Supported

Supported

Supported

Mandarin Chinese

Shiyinshi V1 - End-to-end model, Education Content Analysis, Medical Content Analysis, News Media Content Analysis, Entertainment Video Content Analysis, Audio and Video Offline Transcription (Upgraded), New Retail Recognition Model, Travel Recognition Model, Automotive

16k

Supported

Supported

Supported

Supported

Supported

Chinese-English Free Talk

16k

Supported

Supported

Supported

Supported

Not supported

Shiyinshi V1 - End-to-end model

8k

Supported

Supported

Supported

Supported

Supported

Southeast Asian Multilingual

16k

Supported

Not supported

Not supported

Not supported

Not supported

Service status codes

For status codes and solutions, see Error codes: File transcription.