SpeechKit Synthesis Service API v3, REST: Synthesizer.UtteranceSynthesis

Статья создана

Обновлена 30 октября 2025 г.

HTTP request
Body parameters
TextTemplate
TextVariable
Hints
AudioTemplate
AudioContent
AudioFormatOptions
RawAudio
ContainerAudio
AudioVariable
DurationHint
Response
AudioChunk
TextChunk

Synthesizing text into speech.

HTTP request

POST https://tts.api.ml.yandexcloud.kz/tts/v3/utteranceSynthesis

Body parameters

{
  "model": "string",
  // Includes only one of the fields `text`, `textTemplate`
  "text": "string",
  "textTemplate": {
    "textTemplate": "string",
    "variables": [
      {
        "variableName": "string",
        "variableValue": "string"
      }
    ]
  },
  // end of the list of possible fields
  "hints": [
    {
      // Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`
      "voice": "string",
      "audioTemplate": {
        "audio": {
          // Includes only one of the fields `content`
          "content": "string",
          // end of the list of possible fields
          "audioSpec": {
            // Includes only one of the fields `rawAudio`, `containerAudio`
            "rawAudio": {
              "audioEncoding": "string",
              "sampleRateHertz": "string"
            },
            "containerAudio": {
              "containerAudioType": "string"
            }
            // end of the list of possible fields
          }
        },
        "textTemplate": {
          "textTemplate": "string",
          "variables": [
            {
              "variableName": "string",
              "variableValue": "string"
            }
          ]
        },
        "variables": [
          {
            "variableName": "string",
            "variableStartMs": "string",
            "variableLengthMs": "string"
          }
        ]
      },
      "speed": "string",
      "volume": "string",
      "role": "string",
      "pitchShift": "string",
      "duration": {
        "policy": "string",
        "durationMs": "string"
      }
      // end of the list of possible fields
    }
  ],
  "outputAudioSpec": {
    // Includes only one of the fields `rawAudio`, `containerAudio`
    "rawAudio": {
      "audioEncoding": "string",
      "sampleRateHertz": "string"
    },
    "containerAudio": {
      "containerAudioType": "string"
    }
    // end of the list of possible fields
  },
  "loudnessNormalizationType": "string",
  "unsafeMode": "boolean"
}

Field	Description
model	string The name of the model. This parameter is only required for specific functionalities, such as SpeechKit Brand Voice Lite or SpeechKit Brand Voice Call Center. If you are not sure whether your use case needs this parameter, do not include it.
text	string Raw text (e.g. "Hello, Alice"). Includes only one of the fields `text`, `textTemplate`. Text to synthesis, one of text synthesis markups.
textTemplate	TextTemplate Text template instance, e.g. `{"Hello, {username}" with username="Alice"}`. Includes only one of the fields `text`, `textTemplate`. Text to synthesis, one of text synthesis markups.
hints[]	Hints Optional hints for synthesis.
outputAudioSpec	AudioFormatOptions Optional. Default: 22050 Hz, linear 16-bit signed little-endian PCM, with WAV header
loudnessNormalizationType	enum (LoudnessNormalizationType) Specifies type of loudness normalization. Optional. Default: `LUFS`. `LOUDNESS_NORMALIZATION_TYPE_UNSPECIFIED` `MAX_PEAK`: The type of normalization, wherein the gain is changed to bring the highest PCM sample value or analog signal peak to a given level. `LUFS`: The type of normalization based on EBU R 128 recommendation.
unsafeMode	boolean Optional. Automatically split long text to several utterances and bill accordingly. Some degradation in service quality is possible.

TextTemplate

Field

Description

textTemplate

string

Template text.

Sample:The {animal} goes to the {place}.

variables[]

TextVariable

Defining variables in template text.

Sample: {animal: cat, place: forest}

TextVariable

Field

Description

variableName

string

The name of the variable.

variableValue

string

The text of the variable.

Hints

Field	Description
voice	string Name of speaker to use. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
audioTemplate	AudioTemplate Template for synthesizing. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
speed	string Hint to change speed. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
volume	string Hint to regulate normalization level. For `MAX_PEAK` loudness_normalization_type: volume changes in a range (0;1], default value is 0.7. For `LUFS` loudness_normalization_type: volume changes in a range [-145;0), default value is -19. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
role	string Hint to specify pronunciation character for the speaker. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
pitchShift	string Hint to increase (or decrease) speaker's pitch, measured in Hz. Valid values are in range [-1000;1000], default value is 0. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.
duration	DurationHint Hint to limit both minimum and maximum audio duration. Includes only one of the fields `voice`, `audioTemplate`, `speed`, `volume`, `role`, `pitchShift`, `duration`. The hint for TTS engine to specify synthesised audio characteristics.

AudioTemplate

Field	Description
audio	AudioContent Audio file.
textTemplate	TextTemplate Template and description of its variables.
variables[]	AudioVariable Describing variables in audio.

AudioContent

Field

Description

content

string (bytes)

Bytes with audio data.

Includes only one of the fields content.

The audio source to read the data from.

audioSpec

AudioFormatOptions

Description of the audio format.

AudioFormatOptions

Field

Description

rawAudio

RawAudio

The audio format specified in request parameters.

Includes only one of the fields rawAudio, containerAudio.

containerAudio

ContainerAudio

The audio format specified inside the container metadata.

Includes only one of the fields rawAudio, containerAudio.

RawAudio

Field

Description

audioEncoding

enum (AudioEncoding)

Encoding type.

AUDIO_ENCODING_UNSPECIFIED
LINEAR16_PCM: Audio bit depth 16-bit signed little-endian (Linear PCM).

sampleRateHertz

string (int64)

Sampling frequency of the signal.

ContainerAudio

Field

Description

containerAudioType

enum (ContainerAudioType)

CONTAINER_AUDIO_TYPE_UNSPECIFIED
WAV: Audio bit depth 16-bit signed little-endian (Linear PCM).
OGG_OPUS: Data is encoded using the OPUS audio codec and compressed using the OGG container format.
MP3: Data is encoded using MPEG-1/2 Layer III and compressed using the MP3 container format.

AudioVariable

Field	Description
variableName	string The name of the variable.
variableStartMs	string (int64) Start time of the variable in milliseconds.
variableLengthMs	string (int64) Length of the variable in milliseconds.

DurationHint

Field

Description

policy

enum (DurationHintPolicy)

Type of duration constraint.

DURATION_HINT_POLICY_UNSPECIFIED
EXACT_DURATION: Limit audio duration to exact value.
MIN_DURATION: Limit the minimum audio duration.
MAX_DURATION: Limit the maximum audio duration.

durationMs

string (int64)

Constraint on audio duration in milliseconds.

Response

HTTP Code: 200 - OK

{
  "audioChunk": {
    "data": "string"
  },
  "textChunk": {
    "text": "string"
  },
  "startMs": "string",
  "lengthMs": "string"
}

Field	Description
audioChunk	AudioChunk Part of synthesized audio.
textChunk	TextChunk Part of synthesized text.
startMs	string (int64) Start time of the audio chunk in milliseconds.
lengthMs	string (int64) Length of the audio chunk in milliseconds.

AudioChunk

Field

Description

data

string (bytes)

Sequence of bytes of the synthesized audio in format specified in output_audio_spec.

TextChunk

Field

Description

text

string

Synthesized text.

SpeechKit Synthesis Service API v3, REST: Synthesizer.UtteranceSynthesis

HTTP requestHTTP request

Body parametersBody parameters

TextTemplateTextTemplate

TextVariableTextVariable

HintsHints

AudioTemplateAudioTemplate

AudioContentAudioContent

AudioFormatOptionsAudioFormatOptions

RawAudioRawAudio

ContainerAudioContainerAudio

AudioVariableAudioVariable

DurationHintDurationHint

ResponseResponse

AudioChunkAudioChunk

TextChunkTextChunk

Была ли статья полезна?

HTTP request

Body parameters

TextTemplate

TextVariable

Hints

AudioTemplate

AudioContent

AudioFormatOptions

RawAudio

ContainerAudio

AudioVariable

DurationHint

Response

AudioChunk

TextChunk