Murf subpackage_textToSpeech API
The subpackage_textToSpeech API from Murf — 3 operation(s) for subpackage_texttospeech.
OpenAPI Specification
openapi: 3.1.0
info:
title: API Reference subpackage_auth subpackage_textToSpeech API
version: 1.0.0
servers:
- url: https://api.murf.ai
- url: https://global.api.murf.ai
- url: https://us-east.api.murf.ai
- url: https://us-west.api.murf.ai
- url: https://in.api.murf.ai
- url: https://ca.api.murf.ai
- url: https://kr.api.murf.ai
- url: https://me.api.murf.ai
- url: https://jp.api.murf.ai
- url: https://au.api.murf.ai
- url: https://eu-central.api.murf.ai
- url: https://uk.api.murf.ai
- url: https://sa-east.api.murf.ai
tags:
- name: subpackage_textToSpeech
paths:
/v1/speech/stream:
post:
operationId: stream
summary: Stream Speech
description: 'Synthesize speech with ultra-low latency over a streaming connection.
Choose the `Base URL` from the URL dropdown (Global URL or a pinned Region)
**Note**: Global URL auto-routes to the nearest region.
| Region | URL | Default Concurrency |
| ------------------------- | ---------------------------------------------- | -------------------- |
| Global (Routes to the nearest server) | `https://global.api.murf.ai/v1/speech/stream` | Region specific concurrency |
| US-East | `https://us-east.api.murf.ai/v1/speech/stream` | 15 |
| US-West | `https://us-west.api.murf.ai/v1/speech/stream` | 2 |
| India | `https://in.api.murf.ai/v1/speech/stream` | 2 |
| Canada | `https://ca.api.murf.ai/v1/speech/stream` | 2 |
| South Korea | `https://kr.api.murf.ai/v1/speech/stream` | 2 |
| UAE | `https://me.api.murf.ai/v1/speech/stream` | 2 |
| Japan | `https://jp.api.murf.ai/v1/speech/stream` | 2 |
| Australia | `https://au.api.murf.ai/v1/speech/stream` | 2 |
| EU (Central) | `https://eu-central.api.murf.ai/v1/speech/stream` | 2 |
| UK | `https://uk.api.murf.ai/v1/speech/stream` | 2 |
| South America (São Paulo) | `https://sa-east.api.murf.ai/v1/speech/stream` | 2 |
'
tags:
- subpackage_textToSpeech
parameters:
- name: api-key
in: header
required: false
schema:
type: string
responses:
'200':
description: Ok
content:
application/json:
schema:
$ref: '#/components/schemas/text_to_speech_stream_Response_200'
'400':
description: Bad Request
content:
application/json:
schema:
description: Any type
'402':
description: Expired subscription or character limit exhausted
content:
application/json:
schema:
description: Any type
'403':
description: Invalid or expired token/api-key provided
content:
application/json:
schema:
description: Any type
'500':
description: Internal Server Error
content:
application/json:
schema:
description: Any type
'503':
description: Service Unavailable
content:
application/json:
schema:
description: Any type
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateSpeechStreamingRequest'
/v1/speech/generate:
post:
operationId: generate
summary: Synthesize Speech
description: Returns a url to the generated audio file along with other associated properties.
tags:
- subpackage_textToSpeech
parameters:
- name: api-key
in: header
required: false
schema:
type: string
responses:
'200':
description: Ok
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateSpeechResponse'
'400':
description: Bad Request
content:
application/json:
schema:
description: Any type
'402':
description: Expired subscription or character limit exhausted
content:
application/json:
schema:
description: Any type
'403':
description: Invalid or expired token/api-key provided
content:
application/json:
schema:
description: Any type
'500':
description: Internal Server Error
content:
application/json:
schema:
description: Any type
'503':
description: Service Unavailable
content:
application/json:
schema:
description: Any type
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GenerateSpeechRequest'
/v1/speech/voices:
get:
operationId: get-voices
summary: List Voices
description: Returns a list of available voices for speech synthesis
tags:
- subpackage_textToSpeech
parameters:
- name: model
in: query
description: 'Valid values: FALCON, GEN2'
required: false
schema:
type: string
default: GEN2
- name: token
in: header
required: false
schema:
type: string
- name: api-key
in: header
required: false
schema:
type: string
responses:
'200':
description: Ok
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/ApiVoice'
'400':
description: Bad Request
content:
application/json:
schema:
description: Any type
'403':
description: Invalid or expired token provided
content:
application/json:
schema:
description: Any type
'500':
description: Internal Server Error
content:
application/json:
schema:
description: Any type
'503':
description: Service Unavailable
content:
application/json:
schema:
description: Any type
components:
schemas:
PronunciationDetailType:
type: string
enum:
- IPA
- SAY_AS
title: PronunciationDetailType
GenerateSpeechStreamingRequest:
type: object
properties:
model:
type: string
description: 'The model to use for audio output. Defaults to FALCON for all the regions except US-East. Valid values: FALCON, GEN2'
channelType:
type: string
default: MONO
description: 'Valid values: STEREO, MONO'
format:
type: string
default: WAV
description: 'Format of the generated audio file.Valid values: MP3, FLAC, WAV, ALAW, ULAW, OGG, PCM'
multiNativeLocale:
type: string
description: 'This field is superseded by `locale` field. Please migrate to `locale` field to ensure compatibility with future API versions.
Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively.
Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.'
locale:
type: string
description: 'Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively.
Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.'
pitch:
type: integer
description: Pitch of the voiceover
pronunciationDictionary:
type: object
additionalProperties:
$ref: '#/components/schemas/PronunciationDetail'
description: "An object used to define custom pronunciations. \n\n Example 1: {\"live\":{\"type\": \"IPA\", \"pronunciation\": \"laɪv\"}}. \n\n Example 2: {\"2022\":{\"type\": \"SAY_AS\", \"pronunciation\": \"twenty twenty two\"}}"
rate:
type: integer
description: Speed of the voiceover
sampleRate:
type: number
format: double
default: 24000
description: Valid values are 8000, 16000, 24000, 44100, 48000. Defaults to 24000 for Falcon model and 44100 for Gen2 model.
style:
type: string
description: The voice style to be used for voiceover generation.
text:
type: string
description: The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
variation:
type: integer
default: 1
description: Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
voiceId:
type: string
description: Use the GET /v1/speech/voices API to find supported voiceIds. You can use either the voiceId (e.g. en-US-natalie) or just the voice actor's name (e.g. natalie).
required:
- text
- voiceId
title: GenerateSpeechStreamingRequest
ApiVoice:
type: object
properties:
accent:
type: string
description: This field has been deprecated. Please refer to 'supportedLocales.detail' instead.
availableStyles:
type: array
items:
type: string
description: This field has been deprecated. Please refer to 'supportedLocales.availableStyles' instead.
description:
type: string
displayLanguage:
type: string
description: This field has been deprecated. Please refer to 'supportedLocales.detail' instead.
displayName:
type: string
gender:
$ref: '#/components/schemas/ApiVoiceGender'
locale:
type: string
supportedLocales:
type: object
additionalProperties:
$ref: '#/components/schemas/StyleDetails'
voiceId:
type: string
title: ApiVoice
text_to_speech_stream_Response_200:
type: object
properties: {}
description: Empty response body
title: text_to_speech_stream_Response_200
GenerateSpeechRequestModelVersion:
type: string
enum:
- GEN2
default: GEN2
description: 'Valid values: GEN2. Audio will be generated using the new and advanced GEN2 model. Outputs from GEN2 sound more natural and high-quality compared to earlier models.'
title: GenerateSpeechRequestModelVersion
ApiVoiceGender:
type: string
enum:
- Male
- Female
- NonBinary
title: ApiVoiceGender
PronunciationDetail:
type: object
properties:
pronunciation:
type: string
type:
$ref: '#/components/schemas/PronunciationDetailType'
description: "An object used to define custom pronunciations. \n\n Example 1: {\"live\":{\"type\": \"IPA\", \"pronunciation\": \"laɪv\"}}. \n\n Example 2: {\"2022\":{\"type\": \"SAY_AS\", \"pronunciation\": \"twenty twenty two\"}}"
title: PronunciationDetail
StyleDetails:
type: object
properties:
availableStyles:
type: array
items:
type: string
detail:
type: string
title: StyleDetails
WordDurationResponse:
type: object
properties:
endMs:
type: integer
pitchScaleMaximum:
type: number
format: double
description: This field has been deprecated.
pitchScaleMinimum:
type: number
format: double
description: This field has been deprecated.
sourceWordIndex:
type: integer
description: This field has been deprecated.
startMs:
type: integer
word:
type: string
title: WordDurationResponse
GenerateSpeechResponse:
type: object
properties:
audioFile:
type: string
format: url
audioLengthInSeconds:
type: number
format: double
consumedCharacterCount:
type: integer
format: int64
description: Number of characters consumed so far in the current billing cycle.
encodedAudio:
type: string
remainingCharacterCount:
type: integer
format: int64
description: Remaining number of characters available for synthesis in the current billing cycle.
warning:
type: string
wordDurations:
type: array
items:
$ref: '#/components/schemas/WordDurationResponse'
required:
- audioFile
- audioLengthInSeconds
- remainingCharacterCount
- wordDurations
title: GenerateSpeechResponse
GenerateSpeechRequest:
type: object
properties:
audioDuration:
type: number
format: double
description: This parameter allows specifying the duration (in seconds) for the generated audio. If the value is 0, this parameter will be ignored. Only available for Gen2 model.
channelType:
type: string
default: MONO
description: 'Valid values: STEREO, MONO'
encodeAsBase64:
type: boolean
description: Set to true to receive audio in response as a Base64 encoded string instead of a url. This enables zero retention of audio data on Murf's servers.
format:
type: string
default: WAV
description: 'Format of the generated audio file. Valid values: MP3, WAV, FLAC, ALAW, ULAW, PCM, OGG'
modelVersion:
$ref: '#/components/schemas/GenerateSpeechRequestModelVersion'
description: 'Valid values: GEN2. Audio will be generated using the new and advanced GEN2 model. Outputs from GEN2 sound more natural and high-quality compared to earlier models.'
multiNativeLocale:
type: string
description: 'This field is superseded by `locale` field. Please migrate to `locale` field to ensure compatibility with future API versions.
Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.'
locale:
type: string
description: 'Specifies the language for the generated audio, enabling a voice to speak in multiple languages natively. Only available in the Gen2 model.
Valid values: "en-US", "en-UK", "es-ES", etc. Use the GET /v1/speech/voices endpoint to retrieve the list of available voices and languages.'
pitch:
type: integer
description: Pitch of the voiceover
pronunciationDictionary:
type: object
additionalProperties:
$ref: '#/components/schemas/PronunciationDetail'
description: "An object used to define custom pronunciations. \n\n Example 1: {\"live\":{\"type\": \"IPA\", \"pronunciation\": \"laɪv\"}}. \n\n Example 2: {\"2022\":{\"type\": \"SAY_AS\", \"pronunciation\": \"twenty twenty two\"}}"
rate:
type: integer
description: Speed of the voiceover
sampleRate:
type: number
format: double
default: 44100
description: Valid values are 8000, 24000, 44100, 48000
style:
type: string
description: The voice style to be used for voiceover generation.
text:
type: string
description: The text that is to be synthesised. e.g. 'Hello there [pause 1s] friend'
variation:
type: integer
default: 1
description: Higher values will add more variation in terms of Pause, Pitch, and Speed to the voice. Only available for Gen2 model.
voiceId:
type: string
description: Use the GET /v1/speech/voices API to find supported voiceIds. You can use either the voiceId (e.g. en-US-natalie) or just the voice actor's name (e.g. natalie).
wordDurationsAsOriginalText:
type: boolean
default: false
description: If set to true, the word durations in response will return words as the original input text. (English only)
required:
- text
- voiceId
title: GenerateSpeechRequest