@elevenlabs/elevenlabs-js 2.2.0 → 2.3.0

package/.mock/definition/textToSpeech.yml

@@ -1,959 +0,0 @@
-types:
-  TextToSpeechConvertRequestOutputFormat:
-    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
-  BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization:
-    enum:
-      - auto
-      - 'on'
-      - 'off'
-    docs: >-
-      This parameter controls text normalization with three modes: 'auto', 'on',
-      and 'off'. When set to 'auto', the system will automatically decide
-      whether to apply text normalization (e.g., spelling out numbers). With
-      'on', text normalization will always be applied, while with 'off', it will
-      be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-      'eleven_flash_v2_5' models.
-    default: auto
-    inline: true
-    source:
-      openapi: openapi.json
-  TextToSpeechConvertWithTimestampsRequestOutputFormat:
-    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
-  BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization:
-    enum:
-      - auto
-      - 'on'
-      - 'off'
-    docs: >-
-      This parameter controls text normalization with three modes: 'auto', 'on',
-      and 'off'. When set to 'auto', the system will automatically decide
-      whether to apply text normalization (e.g., spelling out numbers). With
-      'on', text normalization will always be applied, while with 'off', it will
-      be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-      'eleven_flash_v2_5' models.
-    default: auto
-    inline: true
-    source:
-      openapi: openapi.json
-  TextToSpeechStreamRequestOutputFormat:
-    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
-  BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization:
-    enum:
-      - auto
-      - 'on'
-      - 'off'
-    docs: >-
-      This parameter controls text normalization with three modes: 'auto', 'on',
-      and 'off'. When set to 'auto', the system will automatically decide
-      whether to apply text normalization (e.g., spelling out numbers). With
-      'on', text normalization will always be applied, while with 'off', it will
-      be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-      'eleven_flash_v2_5' models.
-    default: auto
-    inline: true
-    source:
-      openapi: openapi.json
-  TextToSpeechStreamWithTimestampsRequestOutputFormat:
-    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
-  BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization:
-    enum:
-      - auto
-      - 'on'
-      - 'off'
-    docs: >-
-      This parameter controls text normalization with three modes: 'auto', 'on',
-      and 'off'. When set to 'auto', the system will automatically decide
-      whether to apply text normalization (e.g., spelling out numbers). With
-      'on', text normalization will always be applied, while with 'off', it will
-      be skipped. Cannot be turned on for 'eleven_turbo_v2_5' or
-      'eleven_flash_v2_5' models.
-    default: auto
-    inline: true
-    source:
-      openapi: openapi.json
-imports:
-  root: __package__.yml
-service:
-  auth: false
-  base-path: ''
-  endpoints:
-    convert:
-      path: /v1/text-to-speech/{voice_id}
-      method: POST
-      auth: false
-      docs: >-
-        Converts text into speech using a voice of your choice and returns
-        audio.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. Use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-      display-name: Create speech
-      request:
-        name: TextToSpeechRequest
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<TextToSpeechConvertRequestOutputFormat>
-            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 speech.
-            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_multilingual_v2
-            language_code:
-              type: optional<string>
-              docs: >-
-                Language code (ISO 639-1) used to enforce a language for the
-                model. Currently only Turbo v2.5 and Flash v2.5 support language
-                enforcement. For other models, an error will be returned if
-                language code is provided.
-            voice_settings:
-              type: optional<root.VoiceSettings>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request.
-            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.
-            previous_text:
-              type: optional<string>
-              docs: >-
-                The text that came before the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            next_text:
-              type: optional<string>
-              docs: >-
-                The text that comes after the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            previous_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that were generated before
-                this generation. Can be used to improve the speech's continuity
-                when splitting up a large task into multiple requests. The
-                results will be best when the same model is used across the
-                generations. In case both previous_text and previous_request_ids
-                is send, previous_text will be ignored. A maximum of 3
-                request_ids can be send.
-            next_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that come after this
-                generation. next_request_ids is especially useful for
-                maintaining the speech's continuity when regenerating a sample
-                that has had some audio quality issues. For example, if you have
-                generated 3 speech clips, and you want to improve clip 2,
-                passing the request id of clip 3 as a next_request_id (and that
-                of clip 1 as a previous_request_id) will help maintain natural
-                flow in the combined speech. The results will be best when the
-                same model is used across the generations. In case both
-                next_text and next_request_ids is send, next_text will be
-                ignored. A maximum of 3 request_ids can be send.
-            use_pvc_as_ivc:
-              type: optional<boolean>
-              docs: >-
-                If true, we won't use PVC version of the voice for the
-                generation but the IVC version. This is a temporary workaround
-                for higher latency in PVC versions.
-              default: false
-              availability: deprecated
-            apply_text_normalization:
-              type: >-
-                optional<BodyTextToSpeechV1TextToSpeechVoiceIdPostApplyTextNormalization>
-              docs: >-
-                This parameter controls text normalization with three modes:
-                'auto', 'on', and 'off'. When set to 'auto', the system will
-                automatically decide whether to apply text normalization (e.g.,
-                spelling out numbers). With 'on', text normalization will always
-                be applied, while with 'off', it will be skipped. Cannot be
-                turned on for 'eleven_turbo_v2_5' or 'eleven_flash_v2_5' models.
-              default: auto
-            apply_language_text_normalization:
-              type: optional<boolean>
-              docs: >-
-                This parameter controls language text normalization. This helps
-                with proper pronunciation of text in some supported languages.
-                WARNING: This parameter can heavily increase the latency of the
-                request. Currently only supported for Japanese.
-              default: false
-        content-type: application/json
-      response:
-        docs: The generated audio file
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: JBFqnCBsd6RMkjVDRZzb
-          query-parameters:
-            output_format: mp3_44100_128
-          request:
-            text: The first move is what sets everything in motion.
-            model_id: eleven_multilingual_v2
-    convert_with_timestamps:
-      path: /v1/text-to-speech/{voice_id}/with-timestamps
-      method: POST
-      auth: false
-      docs: >-
-        Generate speech from text with precise character-level timing
-        information for audio-text synchronization.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            Voice ID to be used, you can use https://api.elevenlabs.io/v1/voices
-            to list all the available voices.
-      display-name: Create speech with timing
-      request:
-        name: TextToSpeechWithTimestampsRequest
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<TextToSpeechConvertWithTimestampsRequestOutputFormat>
-            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 speech.
-            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_multilingual_v2
-            language_code:
-              type: optional<string>
-              docs: >-
-                Language code (ISO 639-1) used to enforce a language for the
-                model. Currently only Turbo v2.5 and Flash v2.5 support language
-                enforcement. For other models, an error will be returned if
-                language code is provided.
-            voice_settings:
-              type: optional<root.VoiceSettings>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request.
-            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.
-            previous_text:
-              type: optional<string>
-              docs: >-
-                The text that came before the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            next_text:
-              type: optional<string>
-              docs: >-
-                The text that comes after the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            previous_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that were generated before
-                this generation. Can be used to improve the speech's continuity
-                when splitting up a large task into multiple requests. The
-                results will be best when the same model is used across the
-                generations. In case both previous_text and previous_request_ids
-                is send, previous_text will be ignored. A maximum of 3
-                request_ids can be send.
-            next_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that come after this
-                generation. next_request_ids is especially useful for
-                maintaining the speech's continuity when regenerating a sample
-                that has had some audio quality issues. For example, if you have
-                generated 3 speech clips, and you want to improve clip 2,
-                passing the request id of clip 3 as a next_request_id (and that
-                of clip 1 as a previous_request_id) will help maintain natural
-                flow in the combined speech. The results will be best when the
-                same model is used across the generations. In case both
-                next_text and next_request_ids is send, next_text will be
-                ignored. A maximum of 3 request_ids can be send.
-            use_pvc_as_ivc:
-              type: optional<boolean>
-              docs: >-
-                If true, we won't use PVC version of the voice for the
-                generation but the IVC version. This is a temporary workaround
-                for higher latency in PVC versions.
-              default: false
-              availability: deprecated
-            apply_text_normalization:
-              type: >-
-                optional<BodyTextToSpeechWithTimestampsV1TextToSpeechVoiceIdWithTimestampsPostApplyTextNormalization>
-              docs: >-
-                This parameter controls text normalization with three modes:
-                'auto', 'on', and 'off'. When set to 'auto', the system will
-                automatically decide whether to apply text normalization (e.g.,
-                spelling out numbers). With 'on', text normalization will always
-                be applied, while with 'off', it will be skipped. Cannot be
-                turned on for 'eleven_turbo_v2_5' or 'eleven_flash_v2_5' models.
-              default: auto
-            apply_language_text_normalization:
-              type: optional<boolean>
-              docs: >-
-                This parameter controls language text normalization. This helps
-                with proper pronunciation of text in some supported languages.
-                WARNING: This parameter can heavily increase the latency of the
-                request. Currently only supported for Japanese.
-              default: false
-        content-type: application/json
-      response:
-        docs: Successful Response
-        type: root.AudioWithTimestampsResponse
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: 21m00Tcm4TlvDq8ikWAM
-          request:
-            text: This is a test for the API of ElevenLabs.
-          response:
-            body:
-              audio_base64: base64_encoded_audio_string
-              alignment:
-                characters:
-                  - H
-                  - e
-                  - l
-                  - l
-                  - o
-                character_start_times_seconds:
-                  - 0
-                  - 0.1
-                  - 0.2
-                  - 0.3
-                  - 0.4
-                character_end_times_seconds:
-                  - 0.1
-                  - 0.2
-                  - 0.3
-                  - 0.4
-                  - 0.5
-              normalized_alignment:
-                characters:
-                  - H
-                  - e
-                  - l
-                  - l
-                  - o
-                character_start_times_seconds:
-                  - 0
-                  - 0.1
-                  - 0.2
-                  - 0.3
-                  - 0.4
-                character_end_times_seconds:
-                  - 0.1
-                  - 0.2
-                  - 0.3
-                  - 0.4
-                  - 0.5
-    stream:
-      path: /v1/text-to-speech/{voice_id}/stream
-      method: POST
-      auth: false
-      docs: >-
-        Converts text into speech using a voice of your choice and returns audio
-        as an audio stream.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. Use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-      display-name: Stream speech
-      request:
-        name: StreamTextToSpeechRequest
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<TextToSpeechStreamRequestOutputFormat>
-            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 speech.
-            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_multilingual_v2
-            language_code:
-              type: optional<string>
-              docs: >-
-                Language code (ISO 639-1) used to enforce a language for the
-                model. Currently only Turbo v2.5 and Flash v2.5 support language
-                enforcement. For other models, an error will be returned if
-                language code is provided.
-            voice_settings:
-              type: optional<root.VoiceSettings>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request.
-            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.
-            previous_text:
-              type: optional<string>
-              docs: >-
-                The text that came before the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            next_text:
-              type: optional<string>
-              docs: >-
-                The text that comes after the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            previous_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that were generated before
-                this generation. Can be used to improve the speech's continuity
-                when splitting up a large task into multiple requests. The
-                results will be best when the same model is used across the
-                generations. In case both previous_text and previous_request_ids
-                is send, previous_text will be ignored. A maximum of 3
-                request_ids can be send.
-            next_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that come after this
-                generation. next_request_ids is especially useful for
-                maintaining the speech's continuity when regenerating a sample
-                that has had some audio quality issues. For example, if you have
-                generated 3 speech clips, and you want to improve clip 2,
-                passing the request id of clip 3 as a next_request_id (and that
-                of clip 1 as a previous_request_id) will help maintain natural
-                flow in the combined speech. The results will be best when the
-                same model is used across the generations. In case both
-                next_text and next_request_ids is send, next_text will be
-                ignored. A maximum of 3 request_ids can be send.
-            use_pvc_as_ivc:
-              type: optional<boolean>
-              docs: >-
-                If true, we won't use PVC version of the voice for the
-                generation but the IVC version. This is a temporary workaround
-                for higher latency in PVC versions.
-              default: false
-              availability: deprecated
-            apply_text_normalization:
-              type: >-
-                optional<BodyTextToSpeechStreamingV1TextToSpeechVoiceIdStreamPostApplyTextNormalization>
-              docs: >-
-                This parameter controls text normalization with three modes:
-                'auto', 'on', and 'off'. When set to 'auto', the system will
-                automatically decide whether to apply text normalization (e.g.,
-                spelling out numbers). With 'on', text normalization will always
-                be applied, while with 'off', it will be skipped. Cannot be
-                turned on for 'eleven_turbo_v2_5' or 'eleven_flash_v2_5' models.
-              default: auto
-            apply_language_text_normalization:
-              type: optional<boolean>
-              docs: >-
-                This parameter controls language text normalization. This helps
-                with proper pronunciation of text in some supported languages.
-                WARNING: This parameter can heavily increase the latency of the
-                request. Currently only supported for Japanese.
-              default: false
-        content-type: application/json
-      response:
-        docs: Streaming audio data
-        type: file
-        status-code: 200
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: JBFqnCBsd6RMkjVDRZzb
-          query-parameters:
-            output_format: mp3_44100_128
-          request:
-            text: The first move is what sets everything in motion.
-            model_id: eleven_multilingual_v2
-    stream_with_timestamps:
-      path: /v1/text-to-speech/{voice_id}/stream/with-timestamps
-      method: POST
-      auth: false
-      docs: >-
-        Converts text into speech using a voice of your choice and returns a
-        stream of JSONs containing audio as a base64 encoded string together
-        with information on when which character was spoken.
-      source:
-        openapi: openapi.json
-      path-parameters:
-        voice_id:
-          type: string
-          docs: >-
-            ID of the voice to be used. Use the [Get
-            voices](/docs/api-reference/voices/search) endpoint list all the
-            available voices.
-      display-name: Stream speech with timing
-      request:
-        name: StreamTextToSpeechWithTimestampsRequest
-        query-parameters:
-          enable_logging:
-            type: optional<boolean>
-            default: true
-            docs: >-
-              When enable_logging is set to false zero retention mode will be
-              used for the request. This will mean history features are
-              unavailable for this request, including request stitching. Zero
-              retention mode may only be used by enterprise customers.
-          optimize_streaming_latency:
-            type: optional<integer>
-            docs: >
-              You can turn on latency optimizations at some cost of quality. The
-              best possible final latency varies by model. Possible values:
-
-              0 - default mode (no latency optimizations)
-
-              1 - normal latency optimizations (about 50% of possible latency
-              improvement of option 3)
-
-              2 - strong latency optimizations (about 75% of possible latency
-              improvement of option 3)
-
-              3 - max latency optimizations
-
-              4 - max latency optimizations, but also with text normalizer
-              turned off for even more latency savings (best latency, but can
-              mispronounce eg numbers and dates).
-
-
-              Defaults to None.
-            availability: deprecated
-          output_format:
-            type: optional<TextToSpeechStreamWithTimestampsRequestOutputFormat>
-            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 speech.
-            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_multilingual_v2
-            language_code:
-              type: optional<string>
-              docs: >-
-                Language code (ISO 639-1) used to enforce a language for the
-                model. Currently only Turbo v2.5 and Flash v2.5 support language
-                enforcement. For other models, an error will be returned if
-                language code is provided.
-            voice_settings:
-              type: optional<root.VoiceSettings>
-              docs: >-
-                Voice settings overriding stored settings for the given voice.
-                They are applied only on the given request.
-            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.
-            previous_text:
-              type: optional<string>
-              docs: >-
-                The text that came before the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            next_text:
-              type: optional<string>
-              docs: >-
-                The text that comes after the text of the current request. Can
-                be used to improve the speech's continuity when concatenating
-                together multiple generations or to influence the speech's
-                continuity in the current generation.
-            previous_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that were generated before
-                this generation. Can be used to improve the speech's continuity
-                when splitting up a large task into multiple requests. The
-                results will be best when the same model is used across the
-                generations. In case both previous_text and previous_request_ids
-                is send, previous_text will be ignored. A maximum of 3
-                request_ids can be send.
-            next_request_ids:
-              type: optional<list<string>>
-              docs: >-
-                A list of request_id of the samples that come after this
-                generation. next_request_ids is especially useful for
-                maintaining the speech's continuity when regenerating a sample
-                that has had some audio quality issues. For example, if you have
-                generated 3 speech clips, and you want to improve clip 2,
-                passing the request id of clip 3 as a next_request_id (and that
-                of clip 1 as a previous_request_id) will help maintain natural
-                flow in the combined speech. The results will be best when the
-                same model is used across the generations. In case both
-                next_text and next_request_ids is send, next_text will be
-                ignored. A maximum of 3 request_ids can be send.
-            use_pvc_as_ivc:
-              type: optional<boolean>
-              docs: >-
-                If true, we won't use PVC version of the voice for the
-                generation but the IVC version. This is a temporary workaround
-                for higher latency in PVC versions.
-              default: false
-              availability: deprecated
-            apply_text_normalization:
-              type: >-
-                optional<BodyTextToSpeechStreamingWithTimestampsV1TextToSpeechVoiceIdStreamWithTimestampsPostApplyTextNormalization>
-              docs: >-
-                This parameter controls text normalization with three modes:
-                'auto', 'on', and 'off'. When set to 'auto', the system will
-                automatically decide whether to apply text normalization (e.g.,
-                spelling out numbers). With 'on', text normalization will always
-                be applied, while with 'off', it will be skipped. Cannot be
-                turned on for 'eleven_turbo_v2_5' or 'eleven_flash_v2_5' models.
-              default: auto
-            apply_language_text_normalization:
-              type: optional<boolean>
-              docs: >-
-                This parameter controls language text normalization. This helps
-                with proper pronunciation of text in some supported languages.
-                WARNING: This parameter can heavily increase the latency of the
-                request. Currently only supported for Japanese.
-              default: false
-        content-type: application/json
-      response-stream:
-        docs: Stream of transcription chunks
-        type: root.StreamingAudioChunkWithTimestampsResponse
-        format: json
-      errors:
-        - root.UnprocessableEntityError
-      examples:
-        - path-parameters:
-            voice_id: JBFqnCBsd6RMkjVDRZzb
-          query-parameters:
-            output_format: mp3_44100_128
-          request:
-            text: The first move is what sets everything in motion.
-            model_id: eleven_multilingual_v2
-  source:
-    openapi: openapi.json