@elevenlabs/elevenlabs-js 2.2.0 → 2.4.0

package/.mock/definition/studio.yml

@@ -1,216 +0,0 @@
-imports:
-  root: __package__.yml
-types:
-  BodyCreatePodcastV1StudioPodcastsPostMode:
-    discriminant: type
-    base-properties: {}
-    docs: >-
-      The type of podcast to generate. Can be 'conversation', an interaction
-      between two voices, or 'bulletin', a monologue.
-    union:
-      conversation:
-        type: root.PodcastConversationMode
-      bulletin:
-        type: root.PodcastBulletinMode
-    source:
-      openapi: openapi.json
-  BodyCreatePodcastV1StudioPodcastsPostSourceItem:
-    discriminant: type
-    base-properties: {}
-    union:
-      text:
-        type: root.PodcastTextSource
-      url:
-        type: root.PodcastUrlSource
-    source:
-      openapi: openapi.json
-  BodyCreatePodcastV1StudioPodcastsPostSource:
-    discriminated: false
-    docs: The source content for the Podcast.
-    union:
-      - type: root.PodcastTextSource
-      - type: root.PodcastUrlSource
-      - list<BodyCreatePodcastV1StudioPodcastsPostSourceItem>
-    source:
-      openapi: openapi.json
-    inline: true
-  BodyCreatePodcastV1StudioPodcastsPostQualityPreset:
-    enum:
-      - standard
-      - high
-      - highest
-      - ultra
-      - ultra_lossless
-    docs: >
-      Output quality of the generated audio. Must be one of:
-
-      standard - standard output format, 128kbps with 44.1kHz sample rate.
-
-      high - high quality output format, 192kbps with 44.1kHz sample rate and
-      major improvements on our side. Using this setting increases the credit
-      cost by 20%.
-
-      ultra - ultra quality output format, 192kbps with 44.1kHz sample rate and
-      highest improvements on our side. Using this setting increases the credit
-      cost by 50%.
-
-      ultra lossless - ultra quality output format, 705.6kbps with 44.1kHz
-      sample rate and highest improvements on our side in a fully lossless
-      format. Using this setting increases the credit cost by 100%.
-    default: standard
-    inline: true
-    source:
-      openapi: openapi.json
-  BodyCreatePodcastV1StudioPodcastsPostDurationScale:
-    enum:
-      - short
-      - default
-      - long
-    docs: |
-      Duration of the generated podcast. Must be one of:
-      short - produces podcasts shorter than 3 minutes.
-      default - produces podcasts roughly between 3-7 minutes.
-      long - prodces podcasts longer than 7 minutes.
-    default: default
-    inline: true
-    source:
-      openapi: openapi.json
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    create_podcast:
-      path: /v1/studio/podcasts
-      method: POST
-      auth: false
-      docs: >-
-        Create and auto-convert a podcast project. Currently, the LLM cost is
-        covered by us but you will still be charged for the audio generation. In
-        the future, you will be charged for both the LLM and audio generation
-        costs.
-      source:
-        openapi: openapi.json
-      display-name: Create Podcast
-      request:
-        name: BodyCreatePodcastV1StudioPodcastsPost
-        body:
-          properties:
-            model_id:
-              type: string
-              docs: >-
-                The ID of the model to be used for this Studio project, you can
-                query GET /v1/models to list all available models.
-            mode:
-              display-name: Mode
-              type: BodyCreatePodcastV1StudioPodcastsPostMode
-              docs: >-
-                The type of podcast to generate. Can be 'conversation', an
-                interaction between two voices, or 'bulletin', a monologue.
-            source:
-              display-name: Source
-              type: BodyCreatePodcastV1StudioPodcastsPostSource
-              docs: The source content for the Podcast.
-            quality_preset:
-              type: optional<BodyCreatePodcastV1StudioPodcastsPostQualityPreset>
-              docs: >
-                Output quality of the generated audio. Must be one of:
-
-                standard - standard output format, 128kbps with 44.1kHz sample
-                rate.
-
-                high - high quality output format, 192kbps with 44.1kHz sample
-                rate and major improvements on our side. Using this setting
-                increases the credit cost by 20%.
-
-                ultra - ultra quality output format, 192kbps with 44.1kHz sample
-                rate and highest improvements on our side. Using this setting
-                increases the credit cost by 50%.
-
-                ultra lossless - ultra quality output format, 705.6kbps with
-                44.1kHz sample rate and highest improvements on our side in a
-                fully lossless format. Using this setting increases the credit
-                cost by 100%.
-              default: standard
-            duration_scale:
-              type: optional<BodyCreatePodcastV1StudioPodcastsPostDurationScale>
-              docs: |
-                Duration of the generated podcast. Must be one of:
-                short - produces podcasts shorter than 3 minutes.
-                default - produces podcasts roughly between 3-7 minutes.
-                long - prodces podcasts longer than 7 minutes.
-              default: default
-            language:
-              type: optional<string>
-              docs: >-
-                An optional language of the Studio project. Two-letter language
-                code (ISO 639-1).
-              validation:
-                minLength: 2
-                maxLength: 2
-            highlights:
-              type: optional<list<string>>
-              docs: >-
-                A brief summary or highlights of the Studio project's content,
-                providing key points or themes. This should be between 10 and 70
-                characters.
-            callback_url:
-              type: optional<string>
-              docs: >-
-                A url that will be called by our service when the Studio project
-                is converted. Request will contain a json blob containing the
-                status of the conversion
-        content-type: application/json
-      response:
-        docs: Successful Response
-        type: root.PodcastProjectResponseModel
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            model_id: 21m00Tcm4TlvDq8ikWAM
-            mode:
-              conversation:
-                host_voice_id: aw1NgEzBg83R7vgmiJt6
-                guest_voice_id: aw1NgEzBg83R7vgmiJt7
-              type: conversation
-            source:
-              text: This is a test podcast.
-          response:
-            body:
-              project:
-                project_id: aw1NgEzBg83R7vgmiJt6
-                name: My Project
-                create_date_unix: 1714204800
-                default_title_voice_id: JBFqnCBsd6RMkjVDRZzb
-                default_paragraph_voice_id: JBFqnCBsd6RMkjVDRZzb
-                default_model_id: eleven_multilingual_v2
-                last_conversion_date_unix: 1714204800
-                can_be_downloaded: true
-                title: My Project
-                author: John Doe
-                description: This is a description of my project.
-                genres:
-                  - Novel
-                  - Short Story
-                cover_image_url: https://example.com/cover.jpg
-                target_audience: children
-                language: en
-                content_type: Novel
-                original_publication_date: '2025-01-01'
-                mature_content: false
-                isbn_number: 978-90-274-3964-2
-                volume_normalization: true
-                state: default
-                access_level: viewer
-                fiction: fiction
-                quality_check_on: false
-                quality_check_on_when_bulk_convert: false
-                creation_meta:
-                  creation_progress: 0.5
-                  status: pending
-                  type: blank
-                source_type: blank
-                chapters_enabled: true
-  source:
-    openapi: openapi.json

package/.mock/definition/textToDialogue.yml

@@ -1,213 +0,0 @@
-types:
-  TextToDialogueConvertRequestOutputFormat:
-    enum:
-      - mp3_22050_32
-      - mp3_44100_32
-      - mp3_44100_64
-      - mp3_44100_96
-      - mp3_44100_128
-      - mp3_44100_192
-      - pcm_8000
-      - pcm_16000
-      - pcm_22050
-      - pcm_24000
-      - pcm_44100
-      - pcm_48000
-      - ulaw_8000
-      - alaw_8000
-      - opus_48000_32
-      - opus_48000_64
-      - opus_48000_96
-      - opus_48000_128
-      - opus_48000_192
-    docs: >-
-      Output format of the generated audio. Formatted as
-      codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is
-      represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be
-      subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires
-      you to be subscribed to Pro tier or above. Note that the μ-law format
-      (sometimes written mu-law, often approximated as u-law) is commonly used
-      for Twilio audio inputs.
-    default: mp3_44100_128
-    source:
-      openapi: openapi.json
-  TextToDialogueStreamRequestOutputFormat:
-    enum:
-      - mp3_22050_32
-      - mp3_44100_32
-      - mp3_44100_64
-      - mp3_44100_96
-      - mp3_44100_128
-      - mp3_44100_192
-      - pcm_8000
-      - pcm_16000
-      - pcm_22050
-      - pcm_24000
-      - pcm_44100
-      - pcm_48000
-      - ulaw_8000
-      - alaw_8000
-      - opus_48000_32
-      - opus_48000_64
-      - opus_48000_96
-      - opus_48000_128
-      - opus_48000_192
-    docs: >-
-      Output format of the generated audio. Formatted as
-      codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is
-      represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be
-      subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires
-      you to be subscribed to Pro tier or above. Note that the μ-law format
-      (sometimes written mu-law, often approximated as u-law) is commonly used
-      for Twilio audio inputs.
-    default: mp3_44100_128
-    source:
-      openapi: openapi.json
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    convert:
-      path: /v1/text-to-dialogue
-      method: POST
-      auth: false
-      docs: >-
-        <Warning>Eleven v3 API access is currently not publicly available, but
-        will be soon.</Warning><br/>Converts a list of text and voice ID pairs
-        into speech (dialogue) and returns audio.
-      source:
-        openapi: openapi.json
-      display-name: Create dialogue
-      request:
-        name: BodyTextToDialogueMultiVoiceV1TextToDialoguePost
-        query-parameters:
-          output_format:
-            type: optional<TextToDialogueConvertRequestOutputFormat>
-            default: mp3_44100_128
-            docs: >-
-              Output format of the generated audio. Formatted as
-              codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at
-              32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate
-              requires you to be subscribed to Creator tier or above. PCM with
-              44.1kHz sample rate requires you to be subscribed to Pro tier or
-              above. Note that the μ-law format (sometimes written mu-law, often
-              approximated as u-law) is commonly used for Twilio audio inputs.
-        body:
-          properties:
-            inputs:
-              docs: >-
-                A list of dialogue inputs, each containing text and a voice ID
-                which will be converted into speech.
-              type: list<root.DialogueInput>
-            model_id:
-              type: optional<string>
-              docs: >-
-                Identifier of the model that will be used, you can query them
-                using GET /v1/models. The model needs to have support for text
-                to speech, you can check this using the can_do_text_to_speech
-                property.
-              default: eleven_v3
-            settings:
-              type: optional<root.ModelSettingsResponseModel>
-              docs: Settings controlling the dialogue generation.
-            pronunciation_dictionary_locators:
-              type: optional<list<root.PronunciationDictionaryVersionLocator>>
-              docs: >-
-                A list of pronunciation dictionary locators (id, version_id) to
-                be applied to the text. They will be applied in order. You may
-                have up to 3 locators per request
-            seed:
-              type: optional<integer>
-              docs: >-
-                If specified, our system will make a best effort to sample
-                deterministically, such that repeated requests with the same
-                seed and parameters should return the same result. Determinism
-                is not guaranteed. Must be integer between 0 and 4294967295.
-        content-type: application/json
-      response:
-        docs: The generated audio file
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            inputs:
-              - text: Knock knock
-                voice_id: JBFqnCBsd6RMkjVDRZzb
-              - text: Who is there?
-                voice_id: Aw4FAjKCGjjNkVhN1Xmq
-    stream:
-      path: /v1/text-to-dialogue/stream
-      method: POST
-      auth: false
-      docs: >-
-        <Warning>Eleven v3 API access is currently not publicly available, but
-        will be soon.</Warning><br/>Converts a list of text and voice ID pairs
-        into speech (dialogue) and returns an audio stream.
-      source:
-        openapi: openapi.json
-      display-name: Stream dialogue
-      request:
-        name: BodyTextToDialogueMultiVoiceStreamingV1TextToDialogueStreamPost
-        query-parameters:
-          output_format:
-            type: optional<TextToDialogueStreamRequestOutputFormat>
-            default: mp3_44100_128
-            docs: >-
-              Output format of the generated audio. Formatted as
-              codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at
-              32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate
-              requires you to be subscribed to Creator tier or above. PCM with
-              44.1kHz sample rate requires you to be subscribed to Pro tier or
-              above. Note that the μ-law format (sometimes written mu-law, often
-              approximated as u-law) is commonly used for Twilio audio inputs.
-        body:
-          properties:
-            inputs:
-              docs: >-
-                A list of dialogue inputs, each containing text and a voice ID
-                which will be converted into speech.
-              type: list<root.DialogueInput>
-            model_id:
-              type: optional<string>
-              docs: >-
-                Identifier of the model that will be used, you can query them
-                using GET /v1/models. The model needs to have support for text
-                to speech, you can check this using the can_do_text_to_speech
-                property.
-              default: eleven_v3
-            settings:
-              type: optional<root.ModelSettingsResponseModel>
-              docs: Settings controlling the dialogue generation.
-            pronunciation_dictionary_locators:
-              type: optional<list<root.PronunciationDictionaryVersionLocator>>
-              docs: >-
-                A list of pronunciation dictionary locators (id, version_id) to
-                be applied to the text. They will be applied in order. You may
-                have up to 3 locators per request
-            seed:
-              type: optional<integer>
-              docs: >-
-                If specified, our system will make a best effort to sample
-                deterministically, such that repeated requests with the same
-                seed and parameters should return the same result. Determinism
-                is not guaranteed. Must be integer between 0 and 4294967295.
-        content-type: application/json
-      response:
-        docs: Streaming audio data
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            inputs:
-              - text: Knock knock
-                voice_id: JBFqnCBsd6RMkjVDRZzb
-              - text: Who is there?
-                voice_id: Aw4FAjKCGjjNkVhN1Xmq
-  source:
-    openapi: openapi.json

package/.mock/definition/textToSoundEffects.yml

@@ -1,92 +0,0 @@
-types:
-  TextToSoundEffectsConvertRequestOutputFormat:
-    enum:
-      - mp3_22050_32
-      - mp3_44100_32
-      - mp3_44100_64
-      - mp3_44100_96
-      - mp3_44100_128
-      - mp3_44100_192
-      - pcm_8000
-      - pcm_16000
-      - pcm_22050
-      - pcm_24000
-      - pcm_44100
-      - pcm_48000
-      - ulaw_8000
-      - alaw_8000
-      - opus_48000_32
-      - opus_48000_64
-      - opus_48000_96
-      - opus_48000_128
-      - opus_48000_192
-    docs: >-
-      Output format of the generated audio. Formatted as
-      codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at 32kbs is
-      represented as mp3_22050_32. MP3 with 192kbps bitrate requires you to be
-      subscribed to Creator tier or above. PCM with 44.1kHz sample rate requires
-      you to be subscribed to Pro tier or above. Note that the μ-law format
-      (sometimes written mu-law, often approximated as u-law) is commonly used
-      for Twilio audio inputs.
-    default: mp3_44100_128
-    source:
-      openapi: openapi.json
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    convert:
-      path: /v1/sound-generation
-      method: POST
-      auth: false
-      docs: >-
-        Turn text into sound effects for your videos, voice-overs or video games
-        using the most advanced sound effects model in the world.
-      source:
-        openapi: openapi.json
-      display-name: Create sound effect
-      request:
-        name: CreateSoundEffectRequest
-        query-parameters:
-          output_format:
-            type: optional<TextToSoundEffectsConvertRequestOutputFormat>
-            default: mp3_44100_128
-            docs: >-
-              Output format of the generated audio. Formatted as
-              codec_sample_rate_bitrate. So an mp3 with 22.05kHz sample rate at
-              32kbs is represented as mp3_22050_32. MP3 with 192kbps bitrate
-              requires you to be subscribed to Creator tier or above. PCM with
-              44.1kHz sample rate requires you to be subscribed to Pro tier or
-              above. Note that the μ-law format (sometimes written mu-law, often
-              approximated as u-law) is commonly used for Twilio audio inputs.
-        body:
-          properties:
-            text:
-              type: string
-              docs: The text that will get converted into a sound effect.
-            duration_seconds:
-              type: optional<double>
-              docs: >-
-                The duration of the sound which will be generated in seconds.
-                Must be at least 0.5 and at most 22. If set to None we will
-                guess the optimal duration using the prompt. Defaults to None.
-            prompt_influence:
-              type: optional<double>
-              docs: >-
-                A higher prompt influence makes your generation follow the
-                prompt more closely while also making generations less variable.
-                Must be a value between 0 and 1. Defaults to 0.3.
-        content-type: application/json
-      response:
-        docs: The generated sound effect as an MP3 file
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - request:
-            text: Spacious braam suitable for high-impact movie trailer moments
-  source:
-    openapi: openapi.json