Podcastle Text to Speech API
Synthesize speech from text in batch, streaming, or with word timestamps.
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/podcastle-text-to-speech-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
title: Async (Podcastle) Voice Text to Speech API
description: The Async Voice API is the developer platform behind Podcastle's AI audio engine. It exposes low-latency, human-like text-to-speech, a browsable voice library, and instant voice cloning. Podcastle.ai rebranded its developer platform as Async; the API is served from https://api.async.com and authenticated with an x-api-key header plus a version header. Only documented endpoints and fields are modeled here; no endpoints are fabricated.
termsOfService: https://async.com/terms
contact:
name: Async Support
url: https://docs.async.com
version: v1
servers:
- url: https://api.async.com
description: Async Voice API production base URL
security:
- apiKey: []
tags:
- name: Text to Speech
description: Synthesize speech from text in batch, streaming, or with word timestamps.
paths:
/text_to_speech:
post:
operationId: createSpeech
tags:
- Text to Speech
summary: Generate audio from the input text.
description: Converts a full transcript into a single audio file. On this endpoint only async_flash_v1.0 is documented as supported.
parameters:
- $ref: '#/components/parameters/Version'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/TextToSpeechRequest'
responses:
'200':
description: Audio file in the requested container format.
content:
audio/mpeg:
schema:
type: string
format: binary
audio/wav:
schema:
type: string
format: binary
application/octet-stream:
schema:
type: string
format: binary
'400':
$ref: '#/components/responses/Error'
'401':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
'500':
$ref: '#/components/responses/Error'
/text_to_speech/streaming:
post:
operationId: createSpeechStreaming
tags:
- Text to Speech
summary: Stream audio while it is being generated.
description: Streams synthesized audio as it is generated, returning binary chunks as an octet-stream. Supports async_pro_v1.0, async_flash_v1.5, and async_flash_v1.0.
parameters:
- $ref: '#/components/parameters/Version'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/TextToSpeechRequest'
responses:
'200':
description: Binary audio stream.
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
$ref: '#/components/responses/Error'
'401':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
'500':
$ref: '#/components/responses/Error'
/text_to_speech/with_timestamps:
post:
operationId: createSpeechWithTimestamps
tags:
- Text to Speech
summary: Generate audio with word-level timestamps.
description: Returns base64-encoded audio plus a word-level alignment object with per-word start and end times in milliseconds. On this endpoint only async_flash_v1.0 is documented as supported.
parameters:
- $ref: '#/components/parameters/Version'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/TextToSpeechRequest'
responses:
'200':
description: Audio with word alignment.
content:
application/json:
schema:
$ref: '#/components/schemas/TimestampedSpeechResponse'
'400':
$ref: '#/components/responses/Error'
'401':
$ref: '#/components/responses/Error'
'404':
$ref: '#/components/responses/Error'
'429':
$ref: '#/components/responses/Error'
'500':
$ref: '#/components/responses/Error'
components:
schemas:
Voice:
type: object
properties:
mode:
type: string
description: Voice selection mode.
enum:
- id
id:
type: string
description: Voice identifier from the voice library.
required:
- mode
- id
OutputFormat:
type: object
properties:
container:
type: string
description: Audio container format.
enum:
- raw
- mp3
- wav
encoding:
type: string
description: PCM encoding (used with the raw container).
enum:
- pcm_f32le
- pcm_s16le
- pcm_mulaw
default: pcm_s16le
sample_rate:
type: integer
description: Sample rate in Hz.
minimum: 8000
maximum: 48000
bit_rate:
type: integer
description: Bit rate in bits per second (MP3 only).
minimum: 32000
maximum: 320000
default: 192000
required:
- container
- sample_rate
TimestampedSpeechResponse:
type: object
properties:
audio_base64:
type: string
description: Base64-encoded audio in the requested format.
alignment:
type: object
description: Word-level timing aligned with the synthesized audio.
properties:
words:
type: array
items:
type: string
word_start_times_milliseconds:
type: array
items:
type: number
word_end_times_milliseconds:
type: array
items:
type: number
TextToSpeechRequest:
type: object
properties:
model_id:
type: string
description: Synthesis model. async_pro_v1.0 (English, highest quality), async_flash_v1.5 (six languages, optimized for speed), and async_flash_v1.0 (legacy, fifteen languages). The batch and with_timestamps endpoints document support for async_flash_v1.0.
enum:
- async_pro_v1.0
- async_flash_v1.5
- async_flash_v1.0
transcript:
type: string
description: The text to convert to speech.
voice:
$ref: '#/components/schemas/Voice'
output_format:
$ref: '#/components/schemas/OutputFormat'
language:
type: string
description: Force synthesis in the specified language (ISO 639-1).
speed_control:
type: number
description: Playback speed multiplier.
minimum: 0.7
maximum: 2.0
stability:
type: integer
description: Voice stability.
minimum: 0
maximum: 100
required:
- model_id
- transcript
- voice
- output_format
Error:
type: object
properties:
detail:
type: object
properties:
error_code:
type: string
message:
type: string
extra:
type: object
parameters:
Version:
name: version
in: header
required: true
description: API version, for example v1.
schema:
type: string
example: v1
responses:
Error:
description: Error response.
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
securitySchemes:
apiKey:
type: apiKey
in: header
name: x-api-key
description: API key issued from the Async developer console.