WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

SpeechRecognize
✖
SpeechRecognize

Updated in 14.1[Experimental]

✖

recognizes speech in audio and returns it as a string.

✖
SpeechRecognize[audio,level]

returns a list of strings at the specified structural level.

✖
SpeechRecognize[audio,level,prop]

returns prop for text at the given level.

Details and Options

  • Speech recognition aims to convert a spoken audio signal to text. It is also known as speech-to-text and is typically used in voice-enabled human-machine interactions and digital personal assistants.
  • SpeechRecognize[audio] returns all recognized speech in audio as a single string.
  • Structural elements specified in level include:
  • Automaticspeech found in the whole audio signal (default)
    "Segment"a list of transcription segments
    "Sentence"a list of sentences
    "Word"a list of words
  • The property prop can be one of the following:
  • "Audio"trimmed audio containing the recognized text
    "Confidence"strength of the recognized text
    "Interval"interval containing the text
    "SubtitleRules"a list of time intervals and texts
    "Text"recognized text (default)
    {prop1,prop2,…}a list of properties
  • The following options can be given:
  • LanguageAutomaticthe language to recognize
    Masking Allinterval of interest
    Method Automaticthe method to use
    PerformanceGoal $PerformanceGoalaspects of performance to try to optimize
    ProgressReporting$ProgressReportingwhether to report the progress of the computation
    TargetDevice"CPU"the device on which to perform recognition
  • Use Languagelang1lang2 to recognize speech assumed to be in language lang1 and return translated text in language lang2.
  • By default, speech in the whole signal is recognized. Use Masking->{int1,int2,…} to limit the recognition to intervals inti.
  • Possible settings for Method are:
  • Automaticautomatic method
    "GoogleSpeech"uses Google speech-to-text
    "NeuralNetwork"uses built-in neural networks
    "OpenAI"uses OpenAI speech-to-text
  • By default, if a method returns non-speech tokens (e.g. [applause]), they are returned in the result. Use Method{method,"NonSpeechReplacement"replacements} to specify different replacements. Use "NonSpeechReplacement""" to remove them.
  • SpeechRecognize works for English speech as well as various other languages, such as Chinese, Dutch, French, Japanese and Spanish.
  • SpeechRecognize uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.
  • SpeechRecognize may download resources that will be stored in your local object store at $LocalBase, and can be listed using LocalObjects[] and removed using ResourceRemove.

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Recognize speech in an audio signal:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-5y2w0k
Out[1]=1

Recognize speech from a recording:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-242snb
Out[1]=1

Scope  (4)Survey of the scope of standard use cases

Basic Uses  (2)

Recognize speech in a short audio track:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-9p4jbh
Out[1]=1
In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-pcz9n
Out[2]=2

Recognize speech in an audio track of a video file:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-0emb15
Out[1]=1

Recognize speech in a non-English language:

In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-nhkjxj
Out[2]=2

Classify the language from the recognized text:

In[3]:=3
✖
https://wolfram.com/xid/0fq236pu2wn7y-wiihtq
Out[3]=3

Classify the language from the original audio:

In[4]:=4
✖
https://wolfram.com/xid/0fq236pu2wn7y-7wpumt
Out[4]=4

Level Specification  (1)

By default, all recognized text is returned as one string:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-qymfux
Out[1]=1
In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-k1wldd
Out[2]=2

Extract a list of recognized sentences:

In[3]:=3
✖
https://wolfram.com/xid/0fq236pu2wn7y-0e94kh
Out[3]=3

Extract a list of words:

In[4]:=4
✖
https://wolfram.com/xid/0fq236pu2wn7y-oouem8
Out[4]=4

Extract a list of segments, typically used for splitting text for subtitles:

In[5]:=5
✖
https://wolfram.com/xid/0fq236pu2wn7y-xgnwzu
Out[5]=5

Properties  (1)

By default, recognized speech is returned as a string or as lists of strings:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-c7r64w
Out[1]=1

Return the speech interval, corresponding chunk of the audio and recognition strength:

In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-up4d5b
Out[2]=2

Options  (3)Common values & functionality for each option

Masking  (1)

Use the Masking option to recognize parts of a signal:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-j6mbm3
In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-phiskt
Out[2]=2

Method  (1)

By default, a local model is used for speech recognition:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-8ovmgw
Out[1]=1

Use OpenAI speech recognition:

In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-mbqjxk
Out[2]=2

Use GoogleSpeech speech recognition:

In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-bujstd
Out[2]=2

PerformanceGoal  (1)

By default, a medium-speed model with moderate quality is used:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-u2b01g
In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-qvqm2h
Out[2]=2

Get the result fast:

In[3]:=3
✖
https://wolfram.com/xid/0fq236pu2wn7y-cusxr6
Out[3]=3

Get the higher-quality result:

In[4]:=4
✖
https://wolfram.com/xid/0fq236pu2wn7y-7vc2ob
Out[4]=4

A balanced speed and quality result:

In[5]:=5
✖
https://wolfram.com/xid/0fq236pu2wn7y-lzjoya
Out[5]=5

Applications  (4)Sample problems that can be solved with this function

Use AudioIntervals to select which parts of the signal to recognize:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-xwcoq6
In[4]:=4
✖
https://wolfram.com/xid/0fq236pu2wn7y-tgpm1s
Out[4]=4
In[5]:=5
✖
https://wolfram.com/xid/0fq236pu2wn7y-guw8p2
Out[5]=5

Interpret a spoken city:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-qx04uz
Out[1]=1

Show the recognized city on the map:

In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-vrwtfy
Out[2]=2

Find the answer from a spoken question in a text:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-voti84
In[2]:=2
✖
https://wolfram.com/xid/0fq236pu2wn7y-6gj9gs
Out[2]=2

Build an automatic assistant based on Wolfram|Alpha:

In[1]:=1
✖
https://wolfram.com/xid/0fq236pu2wn7y-vwfjed
Out[1]=1
Wolfram Research (2019), SpeechRecognize, Wolfram Language function, https://reference.wolfram.com/language/ref/SpeechRecognize.html (updated 2024).
✖
Wolfram Research (2019), SpeechRecognize, Wolfram Language function, https://reference.wolfram.com/language/ref/SpeechRecognize.html (updated 2024).

Text

Wolfram Research (2019), SpeechRecognize, Wolfram Language function, https://reference.wolfram.com/language/ref/SpeechRecognize.html (updated 2024).

✖
Wolfram Research (2019), SpeechRecognize, Wolfram Language function, https://reference.wolfram.com/language/ref/SpeechRecognize.html (updated 2024).

CMS

Wolfram Language. 2019. "SpeechRecognize." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2024. https://reference.wolfram.com/language/ref/SpeechRecognize.html.

✖
Wolfram Language. 2019. "SpeechRecognize." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2024. https://reference.wolfram.com/language/ref/SpeechRecognize.html.

APA

Wolfram Language. (2019). SpeechRecognize. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/SpeechRecognize.html

✖
Wolfram Language. (2019). SpeechRecognize. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/SpeechRecognize.html

BibTeX

@misc{reference.wolfram_2025_speechrecognize, author="Wolfram Research", title="{SpeechRecognize}", year="2024", howpublished="\url{https://reference.wolfram.com/language/ref/SpeechRecognize.html}", note=[Accessed: 16-April-2025 ]}

✖
@misc{reference.wolfram_2025_speechrecognize, author="Wolfram Research", title="{SpeechRecognize}", year="2024", howpublished="\url{https://reference.wolfram.com/language/ref/SpeechRecognize.html}", note=[Accessed: 16-April-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_speechrecognize, organization={Wolfram Research}, title={SpeechRecognize}, year={2024}, url={https://reference.wolfram.com/language/ref/SpeechRecognize.html}, note=[Accessed: 16-April-2025 ]}

✖
@online{reference.wolfram_2025_speechrecognize, organization={Wolfram Research}, title={SpeechRecognize}, year={2024}, url={https://reference.wolfram.com/language/ref/SpeechRecognize.html}, note=[Accessed: 16-April-2025 ]}