GET

/v1/schemas/fish-audio/audio/v1/tts/stream/with-timestamp?kind=output

kind outputactivity audiohash f776a3e5…extracted Nov 10, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
698642cc0dd247e854fa9711b7d1d26916770ad466e2ae77dc9d983379dc5647
{
  "fetchedAt": 1794288623,
  "extractorVersion": "2",
  "verifiedAt": null
}

Response body

5 properties · 5 required · 2 $defs
propertytypedescriptionconstraints
audio_base64*stringBase64 encoded audio chunk. Concatenate every chunk in event order to reconstruct the full audio.
content*stringText content described by this event's latest alignment snapshot. Long input may be split into multiple content chunks in one stream.
alignment*TTSTimestampAlignmentLatest cumulative timestamp snapshot for `chunk_seq`. When present, replace the previous alignment for the same `chunk_seq`; do not append segments. Null means no alignment snapshot has been produced yet or alignment is unavailable.nullable
chunk_seq*integerSequence number of the text chunk described by `alignment`. Clients should bucket alignment snapshots by this value.n ≥ 0
chunk_audio_offset_sec*numberAbsolute start time of this text chunk within the full audio, in seconds.n ≥ 0

Types

2 $defs

TTSTimestampAlignmentobject

segments*TTSTimestampSegment[]Ordered text timing segments for the generated audio.
audio_duration*numberAudio duration in seconds for this alignment's content chunk.

TTSTimestampSegmentobject

text*stringText segment covered by this timing entry.
start*numberSegment start time in seconds.
end*numberSegment end time in seconds.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fish-audio","endpointId":"v1/tts/stream/with-timestamp","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}