Resemble AI subpackage_textToSpeech API
The subpackage_textToSpeech API from Resemble AI — 2 operation(s) for subpackage_texttospeech.
OpenAPI Specification
openapi: 3.1.0
info:
title: API Reference subpackage_account subpackage_textToSpeech API
version: 1.0.0
servers:
- url: https://f.cluster.resemble.ai
- url: https://app.resemble.ai/api/v2
tags:
- name: subpackage_textToSpeech
paths:
/synthesize:
post:
operationId: synthesize
summary: Synchronous text-to-speech synthesis
description: Generate speech synchronously from text or SSML. Returns complete audio as base64.
tags:
- subpackage_textToSpeech
parameters:
- name: Authorization
in: header
description: API token from https://app.resemble.ai/account/api
required: true
schema:
type: string
responses:
'200':
description: Successful synthesis
content:
application/json:
schema:
$ref: '#/components/schemas/Text-to-Speech_synthesize_Response_200'
'400':
description: Bad request
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
'401':
description: Unauthorized
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
type: object
properties:
voice_uuid:
type: string
description: Voice UUID to use for synthesis
project_uuid:
type: string
description: Optional project UUID to store the clip
title:
type: string
description: Optional title for the generated clip
data:
type: string
description: Text or SSML to synthesize (max 3,000 characters)
model:
type: string
description: Model to use for synthesis. Pass `chatterbox-turbo` to use the Turbo model for lower latency and paralinguistic tag support. If not specified, defaults to Chatterbox or Chatterbox Multilingual based on the voice. Note - Chatterbox-Turbo is supported by all Rapid English voices and Pre Built Library voices.
precision:
$ref: '#/components/schemas/SynthesizePostRequestBodyContentApplicationJsonSchemaPrecision'
description: Audio precision for WAV output
output_format:
$ref: '#/components/schemas/SynthesizePostRequestBodyContentApplicationJsonSchemaOutputFormat'
description: Audio output format
sample_rate:
$ref: '#/components/schemas/SynthesizePostRequestBodyContentApplicationJsonSchemaSampleRate'
description: Audio sample rate in Hz
use_hd:
type: boolean
default: false
description: Enable HD synthesis with small latency trade-off
apply_custom_pronunciations:
type: boolean
default: false
description: When true, automatically applies your team's custom pronunciations to matching words in the input text. Defaults to false.
required:
- voice_uuid
- data
/stream:
post:
operationId: stream-synthesize
summary: Streaming text-to-speech synthesis (HTTP)
description: Stream audio as it's generated. Returns chunked WAV data for progressive playback.
tags:
- subpackage_textToSpeech
parameters:
- name: Authorization
in: header
description: API token from https://app.resemble.ai/account/api
required: true
schema:
type: string
responses:
'200':
description: Streaming audio response (chunked WAV)
content:
application/octet-stream:
schema:
type: string
format: binary
'400':
description: Bad request
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
requestBody:
content:
application/json:
schema:
type: object
properties:
voice_uuid:
type: string
description: Voice UUID to use for synthesis
data:
type: string
description: Text or SSML to synthesize (max 2000 characters)
project_uuid:
type: string
description: Optional project UUID to store the clip
model:
type: string
description: Model to use for synthesis. Pass `chatterbox-turbo` to use the Turbo model for lower latency and paralinguistic tag support. If not specified, defaults to Chatterbox or Chatterbox Multilingual based on the voice. Note - Chatterbox-Turbo is supported by all Rapid English voices and Pre Built Library voices.
precision:
$ref: '#/components/schemas/StreamPostRequestBodyContentApplicationJsonSchemaPrecision'
description: Audio precision
sample_rate:
$ref: '#/components/schemas/StreamPostRequestBodyContentApplicationJsonSchemaSampleRate'
description: Audio sample rate in Hz
use_hd:
type: boolean
default: false
description: Enable HD synthesis with small latency trade-off
apply_custom_pronunciations:
type: boolean
default: false
description: When true, automatically applies your team's custom pronunciations to matching words in the input text. Defaults to false.
required:
- voice_uuid
- data
components:
schemas:
AudioTimestamps:
type: object
properties:
graph_chars:
type: array
items:
type: string
description: Grapheme characters
graph_times:
type: array
items:
type: array
items:
type: number
format: double
description: Grapheme timestamps [start, end] in seconds
phon_chars:
type: array
items:
type: string
description: Phoneme characters
phon_times:
type: array
items:
type: array
items:
type: number
format: double
description: Phoneme timestamps [start, end] in seconds
title: AudioTimestamps
Text-to-Speech_synthesize_Response_200:
type: object
properties:
success:
type: boolean
audio_content:
type: string
format: byte
description: Base64-encoded audio bytes
audio_timestamps:
$ref: '#/components/schemas/AudioTimestamps'
duration:
type: number
format: double
description: Audio duration in seconds
synth_duration:
type: number
format: double
description: Raw synthesis time
output_format:
type: string
sample_rate:
type: integer
title:
type: string
issues:
type: array
items:
type: string
title: Text-to-Speech_synthesize_Response_200
Error:
type: object
properties:
success:
type: boolean
error:
type: string
errors:
type: object
additionalProperties:
type: array
items:
type: string
message:
type: string
title: Error
StreamPostRequestBodyContentApplicationJsonSchemaSampleRate:
type: string
enum:
- '8000'
- '16000'
- '22050'
- '32000'
- '44100'
- '48000'
description: Audio sample rate in Hz
title: StreamPostRequestBodyContentApplicationJsonSchemaSampleRate
SynthesizePostRequestBodyContentApplicationJsonSchemaOutputFormat:
type: string
enum:
- wav
- mp3
default: wav
description: Audio output format
title: SynthesizePostRequestBodyContentApplicationJsonSchemaOutputFormat
SynthesizePostRequestBodyContentApplicationJsonSchemaSampleRate:
type: string
enum:
- '8000'
- '16000'
- '22050'
- '32000'
- '44100'
- '48000'
description: Audio sample rate in Hz
title: SynthesizePostRequestBodyContentApplicationJsonSchemaSampleRate
StreamPostRequestBodyContentApplicationJsonSchemaPrecision:
type: string
enum:
- MULAW
- PCM_16
- PCM_24
- PCM_32
default: PCM_32
description: Audio precision
title: StreamPostRequestBodyContentApplicationJsonSchemaPrecision
SynthesizePostRequestBodyContentApplicationJsonSchemaPrecision:
type: string
enum:
- MULAW
- PCM_16
- PCM_24
- PCM_32
default: PCM_32
description: Audio precision for WAV output
title: SynthesizePostRequestBodyContentApplicationJsonSchemaPrecision
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: API token from https://app.resemble.ai/account/api