CAMB.AI

Make lifelike voice-overs, translate and speak text, transcribe and subtitle recordings, dub videos into other languages, and create sound effects, music and custom voices with CAMB.AI.

Actions

Action	What it does
Clone a voice	Make a new voice from a recording of someone speaking, to use in any speech step.
Create subtitles	Make subtitle files for a video in one or more languages, ready to upload with the video.
Delete a voice	Permanently delete one of your own voices, such as one made with 'Clone a voice'.
Dub a video	Dub a video into another language and save the dubbed video, ready to post or share.
Generate a sound effect or music	Describe a sound or a piece of music and get it back as an audio file.
Generate speech	Turn text into a natural voice-over and save it as an audio file a later step can attach, upload or post.
Get a dubbed video	Collect a dub that was still in progress when 'Dub a video' stopped waiting, or check whether it is ready yet.
List voices	List every voice your CAMB.AI account can speak in, your own voices included.
Narrate a long text	Turn an article, chapter or script of any length into one narrated audio file, like an audiobook.
Separate voice from background	Split a recording into two files: the voices on their own, and the music and background sound on their own.
Transcribe a recording	Write down what is said in an audio or video recording, with who said each line and when.
Translate and speak	Translate text into another language and have a voice speak the translation.
Translate text	Translate text into another language.

Clone a voice

Make a new voice from a recording of someone speaking, to use in any speech step. Only clone voices you have permission to use.

Inputs

Voice namenametextRequired: What to call the voice in the Voice list.
RecordingrecordingtextRequired: 10 to 60 seconds of one person speaking clearly, as MP3, WAV, FLAC or AAC: upload it, pick it from an earlier step, or paste a link.
Gendergendertext: The speaker's gender.One of: 2 (Female), 1 (Male), 9 (Neutral), 0 (Not specified). Default: 0.
Ageagenumber: Roughly how old the speaker is. Leave blank for 30.From 1 to 120.
Languagelanguagetext: The language spoken in the recording.
Descriptiondescriptiontext: Optional notes on the voice, such as its tone.
Clean up the recordingclean_up_recordingtrue/false: Remove background noise before cloning.

Outputs

nametext: The new voice's name.
statustext: Status of the action execution ("success" on success).
voice_idnumber: The new voice's id, for the Voice field.

Example output

{
  "name": "Sam",
  "status": "success",
  "voice_id": 190455
}

Create subtitles

Make subtitle files for a video in one or more languages, ready to upload with the video.

Inputs

Video or audio linkmedia_urltextRequired: A public link CAMB.AI can open: a YouTube video, a shared Google Drive file, or a direct link to an MP4, MOV, MP3 or WAV file.
Spoken languagesource_languagetextRequired: The language spoken in it.
Subtitle languagestarget_languageslistRequired: The languages to make subtitles in. Include the spoken language for subtitles of what is actually said.
File formatsubtitle_formattext: SRT works almost everywhere.One of: srt (SRT · most video players, YouTube and Vimeo), vtt (VTT · web video players), txt (Plain text). Default: srt.
Accuracyaccuracytext: Highest takes longer but catches more of what is said.One of: fast (Standard · faster), slow (Highest · takes longer). Default: fast.

Outputs

contenttext: The first language's subtitles as text.
content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: Every subtitle file, in order.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
source_languagetext: Spoken language.
statustext: Status of the action execution ("success" on success).
subtitle_formattext: srt, vtt or txt.
subtitleslist: One saved subtitle file per language.
urltext: Download link for the saved file.

Example output

{
  "content": "1\n00:00:00,500 --> 00:00:02,800\nBienvenidos de nuevo.\n",
  "content_type": "application/x-subrip",
  "document_ref": "doc_6f7e8d9c",
  "documents": [
    {
      "content_type": "application/x-subrip",
      "document_ref": "doc_6f7e8d9c",
      "filename": "subtitles-es-es.srt",
      "size_bytes": 52,
      "url": "/actions/core/serve-document/doc_6f7e8d9c"
    }
  ],
  "filename": "subtitles-es-es.srt",
  "size_bytes": 52,
  "source_language": "en-us",
  "status": "success",
  "subtitle_format": "srt",
  "subtitles": [
    {
      "content": "1\n00:00:00,500 --> 00:00:02,800\nBienvenidos de nuevo.\n",
      "content_type": "application/x-subrip",
      "document_ref": "doc_6f7e8d9c",
      "filename": "subtitles-es-es.srt",
      "language": "es-es",
      "size_bytes": 52,
      "url": "/actions/core/serve-document/doc_6f7e8d9c"
    }
  ],
  "url": "/actions/core/serve-document/doc_6f7e8d9c"
}

Delete a voice

Permanently delete one of your own voices, such as one made with 'Clone a voice'. CAMB.AI's own voices can't be deleted.

Inputs

Voicevoice_idtextRequired: The voice to delete. It must be one of your own.

Outputs

deletedtrue/false: True once it is gone.
statustext: Status of the action execution ("success" on success).
voice_idnumber: The voice deleted.

Example output

{
  "deleted": true,
  "status": "success",
  "voice_id": 190455
}

Dub a video

Dub a video into another language and save the dubbed video, ready to post or share.

Inputs

Video linkvideo_urltextRequired: A public link CAMB.AI can open: a YouTube video, a shared Google Drive file, or a direct link to an MP4 or MOV file. Audio files work too.
Spoken languagesource_languagetextRequired: The language spoken in it.
Dub intotarget_languagetextRequired: The language to dub it into.
Accuracyaccuracytext: Highest takes longer but catches more of what is said.One of: fast (Standard · faster), slow (Highest · takes longer). Default: fast.
Keep background musickeep_background_musictrue/false: On by default. Turn off to drop music playing under the speech.Default: true.

Outputs

audioobject: The dubbed voice track on its own, saved.
content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The dubbed video and voice track.
dub_statustext: done when the dub is ready, processing while it is not.
dubbing_idtext: The dub's ID, for 'Get a dubbed video'.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
statustext: Status of the action execution ("success" on success).
target_languagetext: The dubbed language.
texttext: The dubbed script as one text.
transcriptlist: What is said in the dub, line by line.
urltext: Download link for the saved file.
videoobject: The dubbed video, saved.
video_linktext: CAMB.AI's own link to the dubbed video. It expires.
video_savedtrue/false: False when the video is over 200 MB and was not saved; use video_link instead.

Example output

{
  "audio": {
    "content_type": "audio/wav",
    "document_ref": "doc_7b20e4d2",
    "filename": "camb-dub-es-es-voice.wav",
    "size_bytes": 1921024,
    "url": "/actions/core/serve-document/doc_7b20e4d2"
  },
  "content_type": "video/mp4",
  "document_ref": "doc_7b20e4d1",
  "documents": [
    {
      "content_type": "video/mp4",
      "document_ref": "doc_7b20e4d1",
      "filename": "camb-dub-es-es.mp4",
      "size_bytes": 8912896,
      "url": "/actions/core/serve-document/doc_7b20e4d1"
    },
    {
      "content_type": "audio/wav",
      "document_ref": "doc_7b20e4d2",
      "filename": "camb-dub-es-es-voice.wav",
      "size_bytes": 1921024,
      "url": "/actions/core/serve-document/doc_7b20e4d2"
    }
  ],
  "dub_status": "done",
  "dubbing_id": "a8f3c2e1-4b5d-4e6f-9a7b-1c2d3e4f5a6b",
  "filename": "camb-dub-es-es.mp4",
  "size_bytes": 8912896,
  "status": "success",
  "target_language": "es-es",
  "text": "Bienvenidos de nuevo.",
  "transcript": [
    {
      "end": 2.8,
      "speaker": "SPEAKER_0",
      "start": 0.5,
      "text": "Bienvenidos de nuevo."
    }
  ],
  "url": "/actions/core/serve-document/doc_7b20e4d1",
  "video": {
    "content_type": "video/mp4",
    "document_ref": "doc_7b20e4d1",
    "filename": "camb-dub-es-es.mp4",
    "size_bytes": 8912896,
    "url": "/actions/core/serve-document/doc_7b20e4d1"
  },
  "video_link": "https://storage.camb.ai/runs/48213/dubbed.mp4",
  "video_saved": true
}

Generate a sound effect or music

Describe a sound or a piece of music and get it back as an audio file.

Inputs

DescriptionprompttextRequired: What it should sound like. Short, concrete descriptions work best.
Kindsound_typetext: A sound effect, or music.One of: sound (Sound effect), music. Default: sound.
Length in secondsdurationnumber: How long a sound effect lasts, up to 10 seconds. Leave blank for 8. Music picks its own length.From 1.0 to 10.0.

Outputs

content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The saved audio file, ready to attach.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
sound_typetext: sound or music.
statustext: Status of the action execution ("success" on success).
urltext: Download link for the saved file.

Example output

{
  "content_type": "audio/wav",
  "document_ref": "doc_1a2b3c4d",
  "documents": [
    {
      "content_type": "audio/wav",
      "document_ref": "doc_1a2b3c4d",
      "filename": "camb-sound-rain-on-a-tin-roof.wav",
      "size_bytes": 1536044,
      "url": "/actions/core/serve-document/doc_1a2b3c4d"
    }
  ],
  "filename": "camb-sound-rain-on-a-tin-roof.wav",
  "size_bytes": 1536044,
  "sound_type": "sound",
  "status": "success",
  "url": "/actions/core/serve-document/doc_1a2b3c4d"
}

Generate speech

Turn text into a natural voice-over and save it as an audio file a later step can attach, upload or post.

Inputs

What to saytexttextRequired: The script to read out, up to 3,000 characters. For longer pieces, use 'Narrate a long text'.
Voicevoice_idtext: Which CAMB.AI voice speaks, your own voices included. Leave blank for CAMB.AI's default voice.
LanguagelanguagetextRequired: The language the text is written in; the voice speaks it with this accent. To speak it in another language, use 'Translate and speak'.One of: ab-ge (Abkhazian (Georgia)), fub-cm (Adamawa Fulfulde (Cameroon)), ady-ru (Adyghe (Russia)), af-za (Afrikaans (South Africa)), ala-ng (Alago (Nigeria)), sq-al (Albanian (Albania)), adx-cn (Amdo Tibetan (China)), am-et (Amharic (Ethiopia)), xmv-mg (Antankarana Malagasy (Madagascar)), ar-dz (Arabic (Algeria)), and 305 more. Default: en-us.
Speech modelspeech_modeltext: Leave blank to use CAMB.AI's standard model for your language.One of: mars-8.1-pro-beta (MARS 8.1 Pro · most natural, 300+ languages (beta)), mars-8.1-flash-beta (MARS 8.1 Flash · quicker, 300+ languages (beta)), mars-pro (MARS Pro · natural, 33 languages), mars-flash (MARS Flash · fastest, 33 languages), mars-instruct (MARS Instruct · follows tone directions, 142 languages).
Tone of voicetonetext: Optional directions for the delivery, such as 'Warm, calm and reassuring'. Uses MARS Instruct.
Speedspeednumber: How fast the voice speaks: 1 is its natural pace, 0.5 half as fast, 2 twice as fast. Leave blank for 1.From 0.5 to 2.0.
File formataudio_formattext: WAV plays anywhere and suits editing; AAC is a much smaller file for the web and phones.One of: wav (WAV · plays anywhere, best for editing), aac (AAC · much smaller, for the web and phones), flac (FLAC · lossless, smaller than WAV). Default: wav.

Outputs

audio_formattext: The saved file's format, e.g. wav.
charactersnumber: How many characters were spoken.
content_typetext: The file's media type.
credits_usednumber: CAMB.AI credits this took, when CAMB.AI says.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The saved audio file, ready to attach.
filenametext: Name of the saved file.
languagetext: The language spoken.
size_bytesnumber: Size of the file in bytes.
speech_modeltext: The model that spoke.
statustext: Status of the action execution ("success" on success).
urltext: Download link for the saved file.
voice_idnumber: The voice that spoke.

Example output

{
  "audio_format": "wav",
  "characters": 24,
  "content_type": "audio/wav",
  "credits_used": 24,
  "document_ref": "doc_5d1f0c2a",
  "documents": [
    {
      "content_type": "audio/wav",
      "document_ref": "doc_5d1f0c2a",
      "filename": "camb-speech-welcome-to-the-team.wav",
      "size_bytes": 245804,
      "url": "/actions/core/serve-document/doc_5d1f0c2a"
    }
  ],
  "filename": "camb-speech-welcome-to-the-team.wav",
  "language": "en-us",
  "size_bytes": 245804,
  "speech_model": "mars-flash",
  "status": "success",
  "url": "/actions/core/serve-document/doc_5d1f0c2a",
  "voice_id": 147320
}

Get a dubbed video

Collect a dub that was still in progress when 'Dub a video' stopped waiting, or check whether it is ready yet.

Inputs

Dubbing IDdubbing_idtextRequired: The dubbing ID from 'Dub a video'.

Outputs

audioobject: The dubbed voice track on its own, saved.
content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The dubbed video and voice track.
dub_statustext: done when the dub is ready, processing while it is not.
dubbing_idtext: The dub's ID, for 'Get a dubbed video'.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
statustext: Status of the action execution ("success" on success).
target_languagetext: The dubbed language.
texttext: The dubbed script as one text.
transcriptlist: What is said in the dub, line by line.
urltext: Download link for the saved file.
videoobject: The dubbed video, saved.
video_linktext: CAMB.AI's own link to the dubbed video. It expires.
video_savedtrue/false: False when the video is over 200 MB and was not saved; use video_link instead.

Example output

{
  "audio": {
    "content_type": "audio/wav",
    "document_ref": "doc_7b20e4d2",
    "filename": "camb-dub-es-es-voice.wav",
    "size_bytes": 1921024,
    "url": "/actions/core/serve-document/doc_7b20e4d2"
  },
  "content_type": "video/mp4",
  "document_ref": "doc_7b20e4d1",
  "documents": [
    {
      "content_type": "video/mp4",
      "document_ref": "doc_7b20e4d1",
      "filename": "camb-dub-es-es.mp4",
      "size_bytes": 8912896,
      "url": "/actions/core/serve-document/doc_7b20e4d1"
    },
    {
      "content_type": "audio/wav",
      "document_ref": "doc_7b20e4d2",
      "filename": "camb-dub-es-es-voice.wav",
      "size_bytes": 1921024,
      "url": "/actions/core/serve-document/doc_7b20e4d2"
    }
  ],
  "dub_status": "done",
  "dubbing_id": "a8f3c2e1-4b5d-4e6f-9a7b-1c2d3e4f5a6b",
  "filename": "camb-dub-es-es.mp4",
  "size_bytes": 8912896,
  "status": "success",
  "target_language": "",
  "text": "Bienvenidos de nuevo.",
  "transcript": [
    {
      "end": 2.8,
      "speaker": "SPEAKER_0",
      "start": 0.5,
      "text": "Bienvenidos de nuevo."
    }
  ],
  "url": "/actions/core/serve-document/doc_7b20e4d1",
  "video": {
    "content_type": "video/mp4",
    "document_ref": "doc_7b20e4d1",
    "filename": "camb-dub-es-es.mp4",
    "size_bytes": 8912896,
    "url": "/actions/core/serve-document/doc_7b20e4d1"
  },
  "video_link": "https://storage.camb.ai/runs/48213/dubbed.mp4",
  "video_saved": true
}

List voices

List every voice your CAMB.AI account can speak in, your own voices included.

Inputs

None.

Outputs

countnumber: How many voices there are.
statustext: Status of the action execution ("success" on success).
voiceslist: The voices, as CAMB.AI lists them.

Example output

{
  "count": 1,
  "status": "success",
  "voices": [
    {
      "age": 35,
      "description": "A rich, warm voice brimming with emotion.",
      "gender": "Male",
      "language": "en-us",
      "name": "Gary",
      "voice_id": 147320
    }
  ]
}

Narrate a long text

Turn an article, chapter or script of any length into one narrated audio file, like an audiobook.

Inputs

TexttexttextRequired: The text to narrate. Paste it, pick it from an earlier step, or upload a .txt or .docx file.
LanguagelanguagetextRequired: The language the text is written in.
Narratorvoice_idtext: The voice that narrates. Leave blank for CAMB.AI's default voice.
Titletitletext: Optional. Names the audio file and the narration in CAMB.AI Studio.

Outputs

content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The saved audio file, ready to attach.
duration_secondsnumber: How long the narration runs, in seconds.
filenametext: Name of the saved file.
languagetext: The language narrated.
size_bytesnumber: Size of the file in bytes.
statustext: Status of the action execution ("success" on success).
urltext: Download link for the saved file.
voice_idnumber: The narrator's voice.

Example output

{
  "content_type": "audio/wav",
  "document_ref": "doc_9c4d2e10",
  "documents": [
    {
      "content_type": "audio/wav",
      "document_ref": "doc_9c4d2e10",
      "filename": "camb-the-lighthouse-keeper.wav",
      "size_bytes": 14155776,
      "url": "/actions/core/serve-document/doc_9c4d2e10"
    }
  ],
  "duration_seconds": 312.4,
  "filename": "camb-the-lighthouse-keeper.wav",
  "language": "en-us",
  "size_bytes": 14155776,
  "status": "success",
  "url": "/actions/core/serve-document/doc_9c4d2e10",
  "voice_id": 147320
}

Separate voice from background

Split a recording into two files: the voices on their own, and the music and background sound on their own.

Inputs

RecordingrecordingtextRequired: An MP3, WAV, FLAC or AAC file: upload one, pick one from an earlier step, or paste a link to one.

Outputs

backgroundobject: Everything but the voices.
content_typetext: The file's media type.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The voice file, then the background.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
statustext: Status of the action execution ("success" on success).
urltext: Download link for the saved file.
voiceobject: The voices on their own.

Example output

{
  "background": {
    "content_type": "audio/wav",
    "document_ref": "doc_0a1b2c3e",
    "filename": "interview-background.wav",
    "size_bytes": 2457644,
    "url": "/actions/core/serve-document/doc_0a1b2c3e"
  },
  "content_type": "audio/wav",
  "document_ref": "doc_0a1b2c3d",
  "documents": [
    {
      "content_type": "audio/wav",
      "document_ref": "doc_0a1b2c3d",
      "filename": "interview-voice.wav",
      "size_bytes": 2457644,
      "url": "/actions/core/serve-document/doc_0a1b2c3d"
    },
    {
      "content_type": "audio/wav",
      "document_ref": "doc_0a1b2c3e",
      "filename": "interview-background.wav",
      "size_bytes": 2457644,
      "url": "/actions/core/serve-document/doc_0a1b2c3e"
    }
  ],
  "filename": "interview-voice.wav",
  "size_bytes": 2457644,
  "status": "success",
  "url": "/actions/core/serve-document/doc_0a1b2c3d",
  "voice": {
    "content_type": "audio/wav",
    "document_ref": "doc_0a1b2c3d",
    "filename": "interview-voice.wav",
    "size_bytes": 2457644,
    "url": "/actions/core/serve-document/doc_0a1b2c3d"
  }
}

Transcribe a recording

Write down what is said in an audio or video recording, with who said each line and when.

Inputs

RecordingrecordingtextRequired: The audio or video to transcribe: upload a file, pick one from an earlier step, or paste a public link to one.
Spoken languagelanguagetextRequired: The language spoken in the recording.
Accuracyaccuracytext: Highest takes longer but catches more of what is said.One of: fast (Standard · faster), slow (Highest · takes longer). Default: fast.

Outputs

duration_secondsnumber: When the last line ends, in seconds.
languagetext: The spoken language.
segmentslist: Each line, with its speaker and timing.
speakerslist: The speakers heard, in order of first line.
statustext: Status of the action execution ("success" on success).
texttext: Everything said, as one text.

Example output

{
  "duration_seconds": 3.6,
  "language": "en-us",
  "segments": [
    {
      "end": 1.9,
      "speaker": "SPEAKER_0",
      "start": 0.4,
      "text": "Thanks for joining."
    },
    {
      "end": 3.6,
      "speaker": "SPEAKER_0",
      "start": 2.1,
      "text": "Let's get started."
    }
  ],
  "speakers": [
    "SPEAKER_0"
  ],
  "status": "success",
  "text": "Thanks for joining. Let's get started."
}

Translate and speak

Translate text into another language and have a voice speak the translation. Returns the audio file and the translated text.

Inputs

What to saytexttextRequired: The text to translate and speak.
Fromsource_languagetextRequired: The language the text is written in.
Intotarget_languagetextRequired: The language to speak it in.
Voicevoice_idtext: Which CAMB.AI voice speaks, your own voices included. Leave blank for CAMB.AI's default voice.
Formalityformalitytext: Formal or informal wording, such as 'usted' or 'tú' in Spanish. Leave blank to let CAMB.AI decide.One of: 1 (Formal), 2 (Informal).
Speech modelspeech_modeltext: Leave blank to use CAMB.AI's standard model for your language.One of: mars-8.1-pro-beta (MARS 8.1 Pro · most natural, 300+ languages (beta)), mars-8.1-flash-beta (MARS 8.1 Flash · quicker, 300+ languages (beta)), mars-pro (MARS Pro · natural, 33 languages), mars-flash (MARS Flash · fastest, 33 languages), mars-instruct (MARS Instruct · follows tone directions, 142 languages).
Speedspeednumber: How fast the voice speaks: 1 is its natural pace, 0.5 half as fast, 2 twice as fast. Leave blank for 1.From 0.5 to 2.0.
File formataudio_formattext: WAV plays anywhere and suits editing; AAC is a much smaller file for the web and phones.One of: wav (WAV · plays anywhere, best for editing), aac (AAC · much smaller, for the web and phones), flac (FLAC · lossless, smaller than WAV). Default: wav.

Outputs

audio_formattext: The saved file's format, e.g. wav.
content_typetext: The file's media type.
credits_usednumber: CAMB.AI credits this took, when CAMB.AI says.
document_reftext: Reference to the saved file, for a later step to attach.
documentslist: The saved audio file, ready to attach.
filenametext: Name of the saved file.
size_bytesnumber: Size of the file in bytes.
source_languagetext: Translated from.
speech_modeltext: The model that spoke.
statustext: Status of the action execution ("success" on success).
target_languagetext: Spoken in.
translated_texttext: The translation that was spoken.
urltext: Download link for the saved file.
voice_idnumber: The voice that spoke.

Example output

{
  "audio_format": "wav",
  "content_type": "audio/wav",
  "credits_used": 22,
  "document_ref": "doc_3e9a41b7",
  "documents": [
    {
      "content_type": "audio/wav",
      "document_ref": "doc_3e9a41b7",
      "filename": "camb-es-es-bienvenido-al-equipo.wav",
      "size_bytes": 221228,
      "url": "/actions/core/serve-document/doc_3e9a41b7"
    }
  ],
  "filename": "camb-es-es-bienvenido-al-equipo.wav",
  "size_bytes": 221228,
  "source_language": "en-us",
  "speech_model": "mars-flash",
  "status": "success",
  "target_language": "es-es",
  "translated_text": "\u00a1Bienvenido al equipo!",
  "url": "/actions/core/serve-document/doc_3e9a41b7",
  "voice_id": 147320
}

Translate text

Translate text into another language.

Inputs

TexttexttextRequired: The text to translate.
Fromsource_languagetextRequired: The language the text is written in.
Intotarget_languagetextRequired: The language to translate it into.
Formalityformalitytext: Formal or informal wording, such as 'usted' or 'tú' in Spanish. Leave blank to let CAMB.AI decide.One of: 1 (Formal), 2 (Informal).

Outputs

source_languagetext: Translated from.
statustext: Status of the action execution ("success" on success).
target_languagetext: Translated into.
translated_texttext: The translation.

Example output

{
  "source_language": "en-us",
  "status": "success",
  "target_language": "fr-fr",
  "translated_text": "Votre commande a \u00e9t\u00e9 exp\u00e9di\u00e9e ce matin."
}

ActionsCopy Anchor Link

Clone a voiceCopy Anchor Link

Inputs

Outputs

Create subtitlesCopy Anchor Link

Inputs

Outputs

Delete a voiceCopy Anchor Link

Inputs

Outputs

Dub a videoCopy Anchor Link

Inputs

Outputs

Generate a sound effect or musicCopy Anchor Link

Inputs

Outputs

Generate speechCopy Anchor Link

Inputs

Outputs

Get a dubbed videoCopy Anchor Link

Inputs

Outputs

List voicesCopy Anchor Link

Inputs

Outputs

Narrate a long textCopy Anchor Link

Inputs

Outputs

Separate voice from backgroundCopy Anchor Link

Inputs

Outputs

Transcribe a recordingCopy Anchor Link

Inputs

Outputs

Translate and speakCopy Anchor Link

Inputs

Outputs

Translate textCopy Anchor Link

Inputs

Outputs

On this page

Actions

Clone a voice

Create subtitles

Delete a voice

Dub a video

Generate a sound effect or music

Generate speech

Get a dubbed video

List voices

Narrate a long text

Separate voice from background

Transcribe a recording

Translate and speak

Translate text