Sarj AI Developer API Audio API
The Audio API from Sarj AI Developer API — 3 operation(s) for audio.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/sarj-ai-developer-api-audio-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
OpenAPI Specification
openapi: 3.2.0
info:
title: Sarj Ai Developer Audio API
version: 0.3.0
description: 'Operations tagged Audio across 2 of this provider''s published API definitions: sarj-ai-developer-api-audio-api-openapi.yml, sarj-ai-developer-api-tts-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: https://platform-api.sarj.ai/api/v1
description: Base URL declared by the provider in apis.yml (roadmap#122).
tags:
- name: Audio
paths:
/v1/audio/speech:
post:
summary: Create Speech
description: Generate speech from text.
operationId: create_speech_v1_audio_speech_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SpeechRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- BearerAuth: []
tags:
- Audio
servers:
- url: https://platform-api.sarj.ai/api/v1
description: Base URL declared by the provider in apis.yml (roadmap#122).
/v1/audio/speech/clone:
post:
summary: Create Speech Clone
description: One-shot voice cloning. Upload reference audio + text to synthesize.
operationId: create_speech_clone_v1_audio_speech_clone_post
requestBody:
content:
multipart/form-data:
schema:
$ref: '#/components/schemas/Body_create_speech_clone_v1_audio_speech_clone_post'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- BearerAuth: []
tags:
- Audio
servers:
- url: https://platform-api.sarj.ai/api/v1
description: Base URL declared by the provider in apis.yml (roadmap#122).
/v1/audio/script:
post:
summary: Create Script Audio
description: 'Synthesize multi-speaker script with voice resolution and mixing.
Returns either:
- single_track: Binary audio with metadata headers
- multi_track: JSON with per-speaker tracks and segment timestamps'
operationId: create_script_audio_v1_audio_script_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ScriptRequest'
required: true
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
security:
- BearerAuth: []
tags:
- Audio
servers:
- url: https://platform-api.sarj.ai/api/v1
description: Base URL declared by the provider in apis.yml (roadmap#122).
components:
schemas:
Body_create_speech_clone_v1_audio_speech_clone_post:
properties:
text:
type: string
maxLength: 50000
minLength: 1
title: Text
ref_audio:
type: string
contentMediaType: application/octet-stream
title: Ref Audio
ref_text:
anyOf:
- type: string
- type: 'null'
title: Ref Text
response_format:
type: string
enum:
- mp3
- opus
- aac
- flac
- wav
- pcm
title: Response Format
default: wav
stream:
type: boolean
title: Stream
default: false
speed:
type: number
maximum: 4.0
minimum: 0.25
title: Speed
default: 1.0
num_step:
anyOf:
- type: integer
maximum: 64.0
minimum: 1.0
- type: 'null'
title: Num Step
guidance_scale:
anyOf:
- type: number
maximum: 10.0
minimum: 0.0
- type: 'null'
title: Guidance Scale
denoise:
anyOf:
- type: boolean
- type: 'null'
title: Denoise
t_shift:
anyOf:
- type: number
maximum: 2.0
minimum: 0.0
- type: 'null'
title: T Shift
position_temperature:
anyOf:
- type: number
maximum: 10.0
minimum: 0.0
- type: 'null'
title: Position Temperature
class_temperature:
anyOf:
- type: number
maximum: 2.0
minimum: 0.0
- type: 'null'
title: Class Temperature
duration:
anyOf:
- type: number
maximum: 60.0
minimum: 0.1
- type: 'null'
title: Duration
language:
anyOf:
- type: string
- type: 'null'
title: Language
description: Language code (e.g., 'en', 'vi', 'zh') for multilingual pronunciation
layer_penalty_factor:
anyOf:
- type: number
minimum: 0.0
- type: 'null'
title: Layer Penalty Factor
preprocess_prompt:
anyOf:
- type: boolean
- type: 'null'
title: Preprocess Prompt
postprocess_output:
anyOf:
- type: boolean
- type: 'null'
title: Postprocess Output
audio_chunk_duration:
anyOf:
- type: number
exclusiveMinimum: 0.0
- type: 'null'
title: Audio Chunk Duration
audio_chunk_threshold:
anyOf:
- type: number
exclusiveMinimum: 0.0
- type: 'null'
title: Audio Chunk Threshold
request_timeout_s:
anyOf:
- type: integer
maximum: 600.0
minimum: 1.0
- type: 'null'
title: Request Timeout S
type: object
required:
- text
- ref_audio
title: Body_create_speech_clone_v1_audio_speech_clone_post
VoiceObject:
properties:
id:
type: string
maxLength: 128
minLength: 1
title: Id
type: object
required:
- id
title: VoiceObject
description: 'OpenAI custom voice object: {"id": "..."}.'
ScriptRequest:
properties:
script:
items:
$ref: '#/components/schemas/ScriptSegment'
type: array
maxItems: 100
minItems: 1
title: Script
default_voice:
anyOf:
- type: string
- type: 'null'
title: Default Voice
speed:
type: number
maximum: 4.0
minimum: 0.25
title: Speed
default: 1.0
response_format:
type: string
enum:
- mp3
- opus
- aac
- flac
- wav
- pcm
title: Response Format
default: wav
output_format:
type: string
enum:
- single_track
- multi_track
title: Output Format
default: single_track
pause_between_speakers:
type: number
maximum: 5.0
minimum: 0.0
title: Pause Between Speakers
default: 0.5
on_error:
type: string
enum:
- abort
- skip
title: On Error
default: abort
type: object
required:
- script
title: ScriptRequest
description: Request body for /v1/audio/script endpoint.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
SpeechRequest:
properties:
model:
type: string
const: sarj-tts
title: Model
description: Sarj TTS model identifier. This API serves only `sarj-tts`.
default: sarj-tts
input:
type: string
maxLength: 50000
minLength: 1
title: Input
voice:
anyOf:
- type: string
- $ref: '#/components/schemas/VoiceObject'
title: Voice
description: Voice ID from `GET /v1/voices`, or an object containing that ID.
default: auto
examples:
- ars_male
- ars_fares
- ars_female
- ars_ibrahim_studio_male
speaker:
anyOf:
- type: string
- type: 'null'
title: Speaker
instructions:
anyOf:
- type: string
maxLength: 4096
- type: 'null'
title: Instructions
response_format:
type: string
enum:
- mp3
- opus
- aac
- flac
- wav
- pcm
title: Response Format
default: mp3
speed:
type: number
maximum: 4.0
minimum: 0.25
title: Speed
default: 1.0
stream_format:
anyOf:
- type: string
enum:
- sse
- audio
- type: 'null'
title: Stream Format
stream:
type: boolean
title: Stream
default: false
num_step:
anyOf:
- type: integer
maximum: 64.0
minimum: 1.0
- type: 'null'
title: Num Step
guidance_scale:
anyOf:
- type: number
maximum: 10.0
minimum: 0.0
- type: 'null'
title: Guidance Scale
denoise:
anyOf:
- type: boolean
- type: 'null'
title: Denoise
t_shift:
anyOf:
- type: number
maximum: 2.0
minimum: 0.0
- type: 'null'
title: T Shift
position_temperature:
anyOf:
- type: number
maximum: 10.0
minimum: 0.0
- type: 'null'
title: Position Temperature
class_temperature:
anyOf:
- type: number
maximum: 2.0
minimum: 0.0
- type: 'null'
title: Class Temperature
duration:
anyOf:
- type: number
maximum: 60.0
minimum: 0.1
- type: 'null'
title: Duration
language:
anyOf:
- type: string
- type: 'null'
title: Language
description: Language code (e.g., 'en', 'vi', 'zh') for multilingual pronunciation
layer_penalty_factor:
anyOf:
- type: number
minimum: 0.0
- type: 'null'
title: Layer Penalty Factor
preprocess_prompt:
anyOf:
- type: boolean
- type: 'null'
title: Preprocess Prompt
postprocess_output:
anyOf:
- type: boolean
- type: 'null'
title: Postprocess Output
audio_chunk_duration:
anyOf:
- type: number
exclusiveMinimum: 0.0
- type: 'null'
title: Audio Chunk Duration
audio_chunk_threshold:
anyOf:
- type: number
exclusiveMinimum: 0.0
- type: 'null'
title: Audio Chunk Threshold
request_timeout_s:
anyOf:
- type: integer
maximum: 600.0
minimum: 1.0
- type: 'null'
title: Request Timeout S
type: object
required:
- input
title: SpeechRequest
description: Sarj TTS request body with an OpenAI SDK-compatible shape.
ScriptSegment:
properties:
speaker:
type: string
maxLength: 64
minLength: 1
title: Speaker
text:
type: string
maxLength: 10000
minLength: 1
title: Text
voice:
anyOf:
- type: string
- type: 'null'
title: Voice
speed:
anyOf:
- type: number
maximum: 4.0
minimum: 0.25
- type: 'null'
title: Speed
type: object
required:
- speaker
- text
title: ScriptSegment
description: Single segment in a multi-speaker script.
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
securitySchemes:
BearerAuth:
type: http
scheme: bearer
bearerFormat: API key
x-refined-from:
- sarj-ai-developer-api-audio-api-openapi.yml
- sarj-ai-developer-api-tts-openapi.json