Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

OpenAPI spec for audio api request/response #61

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

OpenAPI spec for audio api request/response #61

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
179 changes: 152 additions & 27 deletions openapi.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -640,6 +640,48 @@ paths:
schema:
$ref: "#/components/schemas/ErrorData"
deprecated: false
/audio/speech:
post:
tags: ["Audio"]
summary: Create audio generation request
description: Generate audio from input text
operationId: audio-speech
requestBody:
content:
application/json:
schema:
$ref: "#/components/schemas/AudioSpeechRequest"
responses:
"200":
description: "OK"
content:
application/octet-stream:
schema:
type: string
format: binary
audio/wav:
schema:
type: string
format: binary
audio/mpeg:
schema:
type: string
format: binary
text/event-stream:
schema:
$ref: "#/components/schemas/AudioSpeechStreamResponse"
"400":
description: "BadRequest"
content:
application/json:
schema:
$ref: "#/components/schemas/ErrorData"
"429":
description: "RateLimit"
content:
application/json:
schema:
$ref: "#/components/schemas/ErrorData"
components:
securitySchemes:
bearerAuth:
Expand Down Expand Up @@ -682,21 +724,21 @@ components:
example: Our solar system orbits the Milky Way galaxy at about 515,000 mph
example:
- {
"title": "Llama",
"text": "The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.",
}
"title": "Llama",
"text": "The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era.",
}
- {
"title": "Panda",
"text": "The giant panda (Ailuropoda melanoleuca), also known as the panda bear or simply panda, is a bear species endemic to China.",
}
"title": "Panda",
"text": "The giant panda (Ailuropoda melanoleuca), also known as the panda bear or simply panda, is a bear species endemic to China.",
}
- {
"title": "Guanaco",
"text": "The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations.",
}
"title": "Guanaco",
"text": "The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations.",
}
- {
"title": "Wild Bactrian camel",
"text": "The wild Bactrian camel (Camelus ferus) is an endangered species of camel endemic to Northwest China and southwestern Mongolia.",
}
"title": "Wild Bactrian camel",
"text": "The wild Bactrian camel (Camelus ferus) is an endangered species of camel endemic to Northwest China and southwestern Mongolia.",
}
top_n:
type: integer
description: The number of top results to return.
Expand Down Expand Up @@ -756,21 +798,21 @@ components:
nullable: true
example:
- {
"index": 0,
"relevance_score": 0.29980177813003117,
"document":
{
"text": '{"title":"Llama","text":"The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era."}',
},
}
"index": 0,
"relevance_score": 0.29980177813003117,
"document":
{
"text": '{"title":"Llama","text":"The llama is a domesticated South American camelid, widely used as a meat and pack animal by Andean cultures since the pre-Columbian era."}',
},
}
- {
"index": 2,
"relevance_score": 0.2752447527354349,
"document":
{
"text": '{"title":"Guanaco","text":"The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations."}',
},
}
"index": 2,
"relevance_score": 0.2752447527354349,
"document":
{
"text": '{"title":"Guanaco","text":"The guanaco is a camelid native to South America, closely related to the llama. Guanacos are one of two wild South American camelids; the other species is the vicuña, which lives at higher elevations."}',
},
}
usage:
$ref: "#/components/schemas/UsageData"
example:
Expand Down Expand Up @@ -1485,6 +1527,89 @@ components:
- $ref: "#/components/schemas/UsageData"
- nullable: true

AudioSpeechRequest:
type: object
required:
- model
- input
properties:
model:
description: >
The name of the model to query.<br>
<br>
[See all of Together AI's chat models](https://docs.together.ai/docs/serverless-models#audio-models)
example: cartesia/audio-v1
anyOf:
- type: string
- type: string
enum:
- Cartesia/Audio-v1
input:
type: string
description: Input text to generate the audio for
maxLength: 4096
voice:
type: string
description: The voice to use for generating the audi. Supported voices are listed [here](https://together.ai/docs/voices)
response_format:
type: string
description: The format of audio output
default: wav
enum:
- mp3
- wav
- raw
language:
type: string
description: Language of input text
default: en
enum:
- en
response_encoding:
type: string
description: Audio encoding of response
default: pcm_f32le
enum:
- pcm_f32le
- pcm_s16le
- pcm_mulaw
- pcm_alaw
sample_rate:
type: number
default: 44100
description: Sampling rate to use for the output audio
stream:
type: boolean
default: false
description: "If true, output is streamed for several characters at a time instead of waiting for the full response. The stream terminates with `data: [DONE]`. If false, return the encoded audio as octet stream"

AudioSpeechStreamResponse:
oneOf:
- $ref: "#/components/schemas/AudioSpeechStreamEvent"
- $ref: "#/components/schemas/StreamSentinel"

AudioSpeechStreamEvent:
type: object
required: [data]
properties:
data:
$ref: "#/components/schemas/AudioSpeechStreamChunk"

AudioSpeechStreamChunk:
type: object
required: [object, model, b64]
properties:
object:
type: string
enum:
- audio.tts.chunk
model:
type: string
example: suno/bark
b64:
type: string
description: base64 encoded audio stream

StreamSentinel:
type: object
required: [data]
Expand Down Expand Up @@ -2139,4 +2264,4 @@ components:
type: number
format: float
default: 0.0
description: The ratio of the final learning rate to the peak learning rate
description: The ratio of the final learning rate to the peak learning rate