Fish Audio API
Generates speech audio from the provided text using Fish Audio Text-to-Speech service
Request Body
application/json
Optionaltext
Requiredstring1
Maximum length: 150
chunk_length
integerChunk length to be used for the speech
200
Minimum: 100
Maximum: 300
format
stringOutput audio format
"opus"
Value in: "wav" | "pcm" | "mp3" | "opus"
mp3_bitrate
numberMP3 Bitrate to be used for the speech
128
opus_bitrate
numberOpus Bitrate to be used for the speech
64
references
array<object>References to be used for the speech, this requires MessagePack serialization, this will override reference_voices and reference_texts
voice
stringReference ID of the reference model o be used for the speech
normalize
booleanWhether to normalize the speech, this will reduce the latency but may reduce performance on numbers and dates
true
latency
stringLatency to be used for the speech, balanced will reduce the latency but may lead to performance degradation
"normal"
Value in: "normal" | "balanced"
token
RequiredstringFish Audio API key for authentication
1
Response Body
Audio file containing the generated speech
TypeScript Definitions
Use the response body type in TypeScript.
response
Requiredunknown