> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fish.audio/llms.txt
> Use this file to discover all available pages before exploring further.
# WebSocket TTS with Timestamps
> Stream text and receive speech with word-level timestamps over WebSocket
Connect to `wss://api.fish.audio/v1/tts/live/with-timestamp` with a WebSocket
client. The endpoint requires a WebSocket upgrade and returns MessagePack
binary frames. A normal HTTP GET request does not start synthesis.
## Before you start
You need a [Fish Audio API key](/developer-guide/getting-started/api-key) and a
WebSocket client that supports custom authentication headers. To run the Python
example on this page, install its dependencies:
```bash theme={null}
pip install ormsgpack websockets
```
Replace `` in the example with your API key and set `reference_id` to your
voice model ID. The `start.request` object accepts the same parameters as the
[Text to Speech API](/api-reference/endpoint/openapi-v1/text-to-speech).
Send text and receive audio concurrently, then keep reading after sending `stop`
until the server sends `finish`.
## Preserve the final timestamps
Process alignment metadata even when an `audio` event contains empty audio bytes:
a trailing event can carry a final alignment correction. Store each non-null
`alignment` by `chunk_seq`, replacing its previous snapshot. A null alignment
does not erase a snapshot you already received.
Add `chunk_audio_offset_sec` to each segment's `start` and `end` to place it on
the session's audio timeline. The optional `time` field measures elapsed server
session time in milliseconds; use the segment timestamps for captions.
After `finish`, you can send another `start` on the same socket. Reset your audio
buffer and stored alignment snapshots for the new session.
## Related endpoints
* [Text to Speech Stream with Timestamps](/api-reference/endpoint/openapi-v1/text-to-speech-stream-with-timestamps): send the full text in one HTTP request and receive audio and timestamps over SSE.
* [WebSocket TTS Streaming](/api-reference/endpoint/websocket/tts-live): stream text and audio without timestamps.
## AsyncAPI
````yaml api-reference/asyncapi.yml ttsLiveWithTimestamps
id: ttsLiveWithTimestamps
title: Tts live with timestamps
description: >
Real-time TTS streaming channel with word-level timestamps. Clients send
text chunks and receive audio chunks with alignment metadata concurrently.
## Connection Headers
- `Authorization: Bearer ` - Required for authentication (see
security section)
- `model: ` - Optional; specifies which TTS model to use (see
bindings). Falls back to `s2.1-pro` when omitted or unrecognized
servers:
- id: production
protocol: wss
host: api.fish.audio
bindings: []
variables: []
address: /v1/tts/live/with-timestamp
parameters: []
bindings:
- protocol: ws
version: latest
value:
headers:
type: object
properties:
model:
type: string
enum:
- s1
- s2-pro
- s2.1-pro
- s2.1-pro-free
- drama-3-preview
description: >-
TTS model to use for this session. If omitted or set to an
unrecognized value, the session falls back to `s2.1-pro`.
schemaProperties:
- name: headers
type: object
required: false
properties:
- name: model
type: string
description: >-
TTS model to use for this session. If omitted or set to an
unrecognized value, the session falls back to `s2.1-pro`.
enumValues:
- s1
- s2-pro
- s2.1-pro
- s2.1-pro-free
- drama-3-preview
required: false
operations:
- &ref_3
id: receiveTimestampedText
title: Receive timestamped text
description: >
Server receives text and control events from the client.
**Event Sequence:**
1. Client sends StartEvent once at the beginning with TTS configuration
2. Client sends TextEvent for each text chunk to synthesize
3. Client optionally sends FlushEvent to force immediate synthesis of
buffered text
4. Client sends CloseEvent when all text has been sent
type: receive
messages:
- &ref_5
id: startEvent
contentType: application/msgpack
payload:
- name: Start TTS Session
description: >
Initiates a TTS streaming session with configuration.
This must be the first message sent after connecting. It contains
all the
configuration for voice, audio format, and generation parameters.
The `request` payload uses the same fields as the HTTP TTS API. In
WebSocket mode, `request.text` is typically empty in the
StartEvent and
the actual text is streamed through subsequent TextEvent messages.
For full parameter details, examples, and model-specific guidance,
see
the HTTP [Text to Speech
API](/api-reference/endpoint/openapi-v1/text-to-speech).
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
- name: request
type: object
description: >
Request payload for text-to-speech synthesis in WebSocket
StartEvent.
It uses the same parameters as the HTTP [Text to Speech
API](/api-reference/endpoint/openapi-v1/text-to-speech).
Supports single-speaker synthesis on all compatible TTS
models.
Multi-speaker dialogue synthesis is available with `s2-pro`
and the S2.1-Pro family.
In WebSocket mode, `text` is usually empty in StartEvent and
the actual
content is sent through subsequent TextEvent messages.
required: true
properties:
- name: text
type: string
description: >
Text to convert to speech. For WebSocket streaming, this
is
typically empty in the StartEvent and the actual text is
sent via
TextEvent messages.
required: true
- name: max_new_tokens
type: integer
description: |
Maximum audio tokens to generate per text chunk.
required: false
- name: temperature
type: number
description: >
Controls expressiveness. Higher is more varied, lower is
more
consistent.
required: false
- name: top_p
type: number
description: |
Controls diversity via nucleus sampling.
required: false
- name: repetition_penalty
type: number
description: >
Penalty for repeating audio patterns. Values above 1.0
reduce
repetition.
required: false
- name: min_chunk_length
type: integer
description: |
Minimum characters before splitting into a new chunk.
required: false
- name: references
type: array
description: >
Inline voice references for zero-shot cloning.
Single-speaker uses
an array of ReferenceAudio. Multi-speaker uses an array of
speaker
arrays. Multi-speaker dialogue is available with `s2-pro`
and the S2.1-Pro family.
See the HTTP Text to Speech API page for detailed
examples.
required: false
properties:
- name: audio
type: string
description: Audio file bytes for the reference sample
required: true
- name: text
type: string
description: >
Transcription of what is spoken in the reference
audio. Should match
exactly what's spoken and include punctuation for
proper prosody.
required: true
- name: reference_id
type: anyOf
description: >
Voice model ID from Fish Audio or your custom models. Use
a string
for single-speaker synthesis, or an array of model IDs for
multi-speaker dialogue on `s2-pro` or an S2.1-Pro model.
When using multiple speakers,
add speaker tags in `text`. See the HTTP Text to Speech
API page
for full examples.
required: false
- name: prosody
type: object
description: Speed and volume adjustments for the output.
required: false
properties:
- name: speed
type: number
description: >
Speaking rate multiplier. Valid range: 0.5 to 2.0. 1.0
= normal
speed, 0.5 = half speed, 2.0 = double speed. Useful
for adjusting
pacing without regenerating audio.
required: false
- name: volume
type: number
description: >
Volume adjustment in decibels (dB). 0 = no change,
positive values
= louder, negative values = quieter.
required: false
- name: normalize_loudness
type: boolean
description: >
Normalize output loudness for more consistent
perceived volume.
Supported on `s2-pro` and the S2.1-Pro family.
required: false
- name: chunk_length
type: integer
description: |
Text segment size for processing.
required: false
- name: condition_on_previous_chunks
type: boolean
description: |
Use previous audio as context for voice consistency.
required: false
- name: normalize
type: boolean
description: >
Normalizes text for English and Chinese, improving
stability for
numbers.
required: false
- name: early_stop_threshold
type: number
description: |
Early stopping threshold for batch processing.
required: false
- name: format
type: string
description: Output audio format.
enumValues:
- wav
- pcm
- mp3
- opus
required: false
- name: sample_rate
type: &ref_1
- integer
- 'null'
description: >
Audio sample rate in Hz. When null, uses the format's
default
(44100 Hz for most formats, 48000 Hz for opus).
required: false
- name: mp3_bitrate
type: integer
description: |
MP3 bitrate in kbps. Only applies when format is mp3.
enumValues:
- 64
- 128
- 192
required: false
- name: opus_bitrate
type: integer
description: >
Opus bitrate in bps. -1000 for automatic. Only applies
when format
is opus.
enumValues:
- -1000
- 24000
- 32000
- 48000
- 64000
required: false
- name: latency
type: string
description: >
Latency-quality trade-off. normal: best quality, balanced:
reduced
latency, low: lowest latency.
enumValues:
- low
- normal
- balanced
required: false
headers: []
jsonPayloadSchema:
type: object
required:
- event
- request
properties:
event:
type: string
const: start
description: Event type identifier
x-parser-schema-id:
request:
type: object
description: >
Request payload for text-to-speech synthesis in WebSocket
StartEvent.
It uses the same parameters as the HTTP [Text to Speech
API](/api-reference/endpoint/openapi-v1/text-to-speech).
Supports single-speaker synthesis on all compatible TTS models.
Multi-speaker dialogue synthesis is available with `s2-pro` and
the S2.1-Pro family.
In WebSocket mode, `text` is usually empty in StartEvent and the
actual
content is sent through subsequent TextEvent messages.
required:
- text
properties:
text:
type: string
description: >
Text to convert to speech. For WebSocket streaming, this is
typically empty in the StartEvent and the actual text is
sent via
TextEvent messages.
x-parser-schema-id:
max_new_tokens:
type: integer
default: 1024
description: |
Maximum audio tokens to generate per text chunk.
x-parser-schema-id:
temperature:
type: number
minimum: 0
maximum: 1
default: 0.7
description: >
Controls expressiveness. Higher is more varied, lower is
more
consistent.
x-parser-schema-id:
top_p:
type: number
minimum: 0
maximum: 1
default: 0.7
description: |
Controls diversity via nucleus sampling.
x-parser-schema-id:
repetition_penalty:
type: number
default: 1.2
description: >
Penalty for repeating audio patterns. Values above 1.0
reduce
repetition.
x-parser-schema-id:
min_chunk_length:
type: integer
minimum: 0
maximum: 100
default: 50
description: |
Minimum characters before splitting into a new chunk.
x-parser-schema-id:
references:
anyOf:
- description: 'Single speaker: array of reference audio samples'
type: array
items: &ref_0
type: object
required:
- audio
- text
properties:
audio:
type: string
format: binary
description: Audio file bytes for the reference sample
x-parser-schema-id:
text:
type: string
description: >
Transcription of what is spoken in the reference
audio. Should match
exactly what's spoken and include punctuation for
proper prosody.
x-parser-schema-id:
x-parser-schema-id: WebSocketReferenceAudio
x-parser-schema-id:
- description: >-
Multiple speakers: array of arrays, where each inner
array contains reference samples for one speaker
type: array
items:
type: array
items: *ref_0
x-parser-schema-id:
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
description: >
Inline voice references for zero-shot cloning.
Single-speaker uses
an array of ReferenceAudio. Multi-speaker uses an array of
speaker
arrays. Multi-speaker dialogue is available with `s2-pro`
and the S2.1-Pro family.
See the HTTP Text to Speech API page for detailed examples.
x-parser-schema-id:
reference_id:
anyOf:
- description: 'Single speaker: voice model ID string'
type: string
x-parser-schema-id:
- description: >-
Multiple speakers: array of voice model IDs, one per
speaker
type: array
items:
type: string
x-parser-schema-id:
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
default: null
description: >
Voice model ID from Fish Audio or your custom models. Use a
string
for single-speaker synthesis, or an array of model IDs for
multi-speaker dialogue on `s2-pro` or an S2.1-Pro model.
When using multiple speakers,
add speaker tags in `text`. See the HTTP Text to Speech API
page
for full examples.
x-parser-schema-id:
prosody:
oneOf:
- type: object
properties:
speed:
type: number
minimum: 0.5
maximum: 2
default: 1
description: >
Speaking rate multiplier. Valid range: 0.5 to 2.0.
1.0 = normal
speed, 0.5 = half speed, 2.0 = double speed. Useful
for adjusting
pacing without regenerating audio.
x-parser-schema-id:
volume:
type: number
minimum: -20
maximum: 20
default: 0
description: >
Volume adjustment in decibels (dB). 0 = no change,
positive values
= louder, negative values = quieter.
x-parser-schema-id:
normalize_loudness:
type: boolean
default: true
description: >
Normalize output loudness for more consistent
perceived volume.
Supported on `s2-pro` and the S2.1-Pro family.
x-parser-schema-id:
x-parser-schema-id: WebSocketProsodyControl
- type: 'null'
x-parser-schema-id:
default: null
description: Speed and volume adjustments for the output.
x-parser-schema-id:
chunk_length:
type: integer
minimum: 100
maximum: 300
default: 300
description: |
Text segment size for processing.
x-parser-schema-id:
condition_on_previous_chunks:
type: boolean
default: true
description: |
Use previous audio as context for voice consistency.
x-parser-schema-id:
normalize:
type: boolean
default: true
description: >
Normalizes text for English and Chinese, improving stability
for
numbers.
x-parser-schema-id:
early_stop_threshold:
type: number
minimum: 0
maximum: 1
default: 1
description: |
Early stopping threshold for batch processing.
x-parser-schema-id:
format:
type: string
enum:
- wav
- pcm
- mp3
- opus
default: mp3
description: Output audio format.
x-parser-schema-id:
sample_rate:
type: *ref_1
default: null
description: >
Audio sample rate in Hz. When null, uses the format's
default
(44100 Hz for most formats, 48000 Hz for opus).
x-parser-schema-id:
mp3_bitrate:
type: integer
enum:
- 64
- 128
- 192
default: 128
description: |
MP3 bitrate in kbps. Only applies when format is mp3.
x-parser-schema-id:
opus_bitrate:
type: integer
enum:
- -1000
- 24000
- 32000
- 48000
- 64000
default: -1000
description: >
Opus bitrate in bps. -1000 for automatic. Only applies when
format
is opus.
x-parser-schema-id:
latency:
type: string
enum:
- low
- normal
- balanced
default: normal
description: >
Latency-quality trade-off. normal: best quality, balanced:
reduced
latency, low: lowest latency.
x-parser-schema-id:
x-parser-schema-id: WebSocketTTSRequest
x-parser-schema-id:
title: Start TTS Session
description: >
Initiates a TTS streaming session with configuration.
This must be the first message sent after connecting. It contains all
the
configuration for voice, audio format, and generation parameters.
The `request` payload uses the same fields as the HTTP TTS API. In
WebSocket mode, `request.text` is typically empty in the StartEvent
and
the actual text is streamed through subsequent TextEvent messages.
For full parameter details, examples, and model-specific guidance, see
the HTTP [Text to Speech
API](/api-reference/endpoint/openapi-v1/text-to-speech).
example: |-
{
"event": "start",
"request": {
"text": "",
"format": "mp3",
"chunk_length": 300,
"reference_id": "9a9cf47702da476aa4629e2506d4a857",
"latency": "normal"
}
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: startEvent
- &ref_6
id: textEvent
contentType: application/msgpack
payload:
- name: Send Text Chunk
description: >
Sends a chunk of text for synthesis.
You can send multiple TextEvent messages in sequence. The server
will buffer
and synthesize text according to the chunk_length parameter from
StartEvent.
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
- name: text
type: string
description: Text chunk to synthesize
required: true
headers: []
jsonPayloadSchema:
type: object
required:
- event
- text
properties:
event:
type: string
const: text
description: Event type identifier
x-parser-schema-id:
text:
type: string
description: Text chunk to synthesize
x-parser-schema-id:
x-parser-schema-id:
title: Send Text Chunk
description: >
Sends a chunk of text for synthesis.
You can send multiple TextEvent messages in sequence. The server will
buffer
and synthesize text according to the chunk_length parameter from
StartEvent.
example: |-
{
"event": "text",
"text": "Hello, this is streaming text. "
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: textEvent
- &ref_7
id: flushEvent
contentType: application/msgpack
payload:
- name: Flush Buffered Text
description: >
Forces immediate synthesis of all buffered text.
Use this when you want audio generated immediately without waiting
for more
text or for the buffer to fill up. Useful for ensuring low latency
in
interactive applications.
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
headers: []
jsonPayloadSchema:
type: object
required:
- event
properties:
event:
type: string
const: flush
description: Event type identifier
x-parser-schema-id:
x-parser-schema-id:
title: Flush Buffered Text
description: >
Forces immediate synthesis of all buffered text.
Use this when you want audio generated immediately without waiting for
more
text or for the buffer to fill up. Useful for ensuring low latency in
interactive applications.
example: |-
{
"event": "flush"
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: flushEvent
- &ref_8
id: closeEvent
contentType: application/msgpack
payload:
- name: End TTS Session
description: >
Signals the end of the text stream.
After sending this event, the server will finish synthesizing any
remaining
buffered text and send a FinishEvent before closing the
connection.
type: object
properties:
- name: event
type: string
description: Event type identifier (note 'stop', not 'close')
required: true
headers: []
jsonPayloadSchema:
type: object
required:
- event
properties:
event:
type: string
const: stop
description: Event type identifier (note 'stop', not 'close')
x-parser-schema-id:
x-parser-schema-id:
title: End TTS Session
description: >
Signals the end of the text stream.
After sending this event, the server will finish synthesizing any
remaining
buffered text and send a FinishEvent before closing the connection.
example: |-
{
"event": "stop"
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: closeEvent
bindings: []
extensions: &ref_2
- id: x-parser-unique-object-id
value: ttsLiveWithTimestamps
- &ref_4
id: sendTimestampedAudio
title: Send timestamped audio
description: >
Server sends audio chunks with word-level alignment metadata and
completion events.
**Event Flow:**
- Server sends TimestampAudioEvent messages as audio is generated
(multiple times)
- Server sends TimestampFinishEvent once when synthesis completes
- Server can send ErrorEvent when it cannot start or continue synthesis
- Clients should ignore unknown events to support future protocol
extensions
type: send
messages:
- &ref_9
id: timestampAudioEvent
contentType: application/msgpack
payload:
- name: Audio Chunk with Timestamps
description: >
Contains generated audio bytes and the latest word-level alignment
snapshot.
Concatenate every `audio` payload in arrival order to reconstruct
the
complete audio. Alignment is cumulative for each `chunk_seq`, and
segment
times are relative to that chunk.
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
- name: audio
type: string
description: >-
Raw audio bytes. The value may be empty on a trailing frame
that only carries a final alignment correction.
required: true
- name: content
type: string
description: Text content of the chunk identified by `chunk_seq`.
required: true
- name: alignment
type: object
description: >-
Cumulative word-level alignment snapshot for `chunk_seq`.
Replace the stored snapshot when this value is non-null; do
not append it.
required: true
properties:
- name: segments
type: array
description: Ordered text timing segments for the generated audio.
required: true
properties:
- name: text
type: string
description: Text segment covered by this timing entry.
required: true
- name: start
type: number
description: >-
Segment start time in seconds, relative to the
beginning of the chunk.
required: true
- name: end
type: number
description: >-
Segment end time in seconds, relative to the beginning
of the chunk.
required: true
- name: audio_duration
type: number
description: >-
Audio duration in seconds for this alignment's content
chunk.
required: true
- name: chunk_seq
type: integer
description: >-
Monotonically non-decreasing sequence number for the text
chunk described by `content` and `alignment`. Do not use it to
attribute audio bytes.
required: true
- name: chunk_audio_offset_sec
type: number
description: >-
Start time of this text chunk within the full audio, in
seconds. Add it to a segment's `start` or `end` to get its
absolute timestamp.
required: true
- name: time
type: number
description: Milliseconds since the server began the session.
required: false
headers: []
jsonPayloadSchema:
type: object
required:
- event
- audio
- content
- alignment
- chunk_seq
- chunk_audio_offset_sec
properties:
event:
type: string
const: audio
description: Event type identifier
x-parser-schema-id:
audio:
type: string
format: binary
description: >-
Raw audio bytes. The value may be empty on a trailing frame that
only carries a final alignment correction.
x-parser-schema-id:
content:
type: string
description: Text content of the chunk identified by `chunk_seq`.
x-parser-schema-id:
alignment:
anyOf:
- type: object
required:
- segments
- audio_duration
properties:
segments:
type: array
description: Ordered text timing segments for the generated audio.
items:
type: object
required:
- text
- start
- end
properties:
text:
type: string
description: Text segment covered by this timing entry.
x-parser-schema-id:
start:
type: number
description: >-
Segment start time in seconds, relative to the
beginning of the chunk.
x-parser-schema-id:
end:
type: number
description: >-
Segment end time in seconds, relative to the
beginning of the chunk.
x-parser-schema-id:
x-parser-schema-id: TimestampSegment
x-parser-schema-id:
audio_duration:
type: number
description: >-
Audio duration in seconds for this alignment's content
chunk.
x-parser-schema-id:
x-parser-schema-id: TimestampAlignment
- type: 'null'
x-parser-schema-id:
description: >-
Cumulative word-level alignment snapshot for `chunk_seq`.
Replace the stored snapshot when this value is non-null; do not
append it.
x-parser-schema-id:
chunk_seq:
type: integer
minimum: 0
description: >-
Monotonically non-decreasing sequence number for the text chunk
described by `content` and `alignment`. Do not use it to
attribute audio bytes.
x-parser-schema-id:
chunk_audio_offset_sec:
type: number
minimum: 0
description: >-
Start time of this text chunk within the full audio, in seconds.
Add it to a segment's `start` or `end` to get its absolute
timestamp.
x-parser-schema-id:
time:
anyOf:
- type: number
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
default: null
description: Milliseconds since the server began the session.
x-parser-schema-id:
x-parser-schema-id:
title: Audio Chunk with Timestamps
description: >
Contains generated audio bytes and the latest word-level alignment
snapshot.
Concatenate every `audio` payload in arrival order to reconstruct the
complete audio. Alignment is cumulative for each `chunk_seq`, and
segment
times are relative to that chunk.
example: |-
{
"event": "audio",
"audio": "",
"content": "Hello there.",
"alignment": {
"segments": [
{
"text": "Hello",
"start": 0,
"end": 0.42
},
{
"text": "there.",
"start": 0.42,
"end": 0.86
}
],
"audio_duration": 0.86
},
"chunk_seq": 0,
"chunk_audio_offset_sec": 0,
"time": 920
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: timestampAudioEvent
- &ref_10
id: timestampFinishEvent
contentType: application/msgpack
payload:
- name: Timestamped Session Complete
description: >
Signals that the timestamped TTS session has completed. After
receiving
this event, you can send another StartEvent on the same
connection.
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
- name: reason
type: string
description: >-
`stop` for normal completion or `error` when the server
aborted synthesis.
enumValues:
- stop
- error
required: true
- name: message
type: string
description: Failure detail. Present when `reason` is `error`.
required: false
- name: time
type: number
description: Milliseconds since the server began the session.
required: false
headers: []
jsonPayloadSchema:
type: object
required:
- event
- reason
properties:
event:
type: string
const: finish
description: Event type identifier
x-parser-schema-id:
reason:
type: string
enum:
- stop
- error
description: >-
`stop` for normal completion or `error` when the server aborted
synthesis.
x-parser-schema-id:
message:
anyOf:
- type: string
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
default: null
description: Failure detail. Present when `reason` is `error`.
x-parser-schema-id:
time:
anyOf:
- type: number
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
default: null
description: Milliseconds since the server began the session.
x-parser-schema-id:
x-parser-schema-id:
title: Timestamped Session Complete
description: >
Signals that the timestamped TTS session has completed. After
receiving
this event, you can send another StartEvent on the same connection.
example: |-
{
"event": "finish",
"reason": "stop",
"time": 5460
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: timestampFinishEvent
- &ref_11
id: errorEvent
contentType: application/msgpack
payload:
- name: Request Error
description: >
Reports a request-level failure, such as an invalid StartEvent, a
missing
voice reference, or a concurrency refusal. The socket closes
afterwards.
type: object
properties:
- name: event
type: string
description: Event type identifier
required: true
- name: error
type: string
description: Failure detail.
required: true
- name: max_concurrency
type: integer
description: >-
Your account's concurrency limit. Present when the connection
is refused for exceeding it.
required: false
headers: []
jsonPayloadSchema:
type: object
required:
- event
- error
properties:
event:
type: string
const: error
description: Event type identifier
x-parser-schema-id:
error:
type: string
description: Failure detail.
x-parser-schema-id:
max_concurrency:
anyOf:
- type: integer
x-parser-schema-id:
- type: 'null'
x-parser-schema-id:
default: null
description: >-
Your account's concurrency limit. Present when the connection is
refused for exceeding it.
x-parser-schema-id:
x-parser-schema-id:
title: Request Error
description: >
Reports a request-level failure, such as an invalid StartEvent, a
missing
voice reference, or a concurrency refusal. The socket closes
afterwards.
example: |-
{
"event": "error",
"error": "Concurrency limit exceeded",
"max_concurrency": 8
}
bindings: []
extensions:
- id: x-parser-unique-object-id
value: errorEvent
bindings: []
extensions: *ref_2
sendOperations:
- *ref_3
receiveOperations:
- *ref_4
sendMessages:
- *ref_5
- *ref_6
- *ref_7
- *ref_8
receiveMessages:
- *ref_9
- *ref_10
- *ref_11
extensions:
- id: x-parser-unique-object-id
value: ttsLiveWithTimestamps
securitySchemes:
- id: bearerAuth
name: bearerAuth
type: http
description: |
API key authentication using Bearer token.
Get your API key from https://fish.audio/app/api-keys
Pass the token in the Authorization header:
`Authorization: Bearer YOUR_API_KEY`
scheme: bearer
extensions: []
````