GET

/v1/schemas/fish-audio/audio/v1/tts/stream/with-timestamp

Accept:

kind inputactivity audiohash 282b4d02…extracted Nov 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `698642cc0dd247e854fa9711b7d1d26916770ad466e2ae77dc9d983379dc5647` { "fetchedAt": 1794288623, "extractorVersion": "2", "verifiedAt": null }

Request body

21 properties · 1 required · 5 $defs

property	type	description	constraints
text*	string	Text to convert to speech.
temperature	number	Controls expressiveness. Higher is more varied, lower is more consistent.	0 ≤ n ≤ 1 · default: 0.7
top_p	number	Controls diversity via nucleus sampling.	0 ≤ n ≤ 1 · default: 0.7
references	ReferenceAudio[] \| ReferenceAudio[][]	Inline voice references for zero-shot cloning. Requires MessagePack (not JSON). For single speaker, provide an array of ReferenceAudio objects. For multiple speakers, provide an array of arrays where each inner array contains references for one speaker. **Mult…	nullable
reference_id	string \| string[]	Voice model ID(s) from Fish Audio library or your custom models. For single-speaker synthesis, provide a string. For multi-speaker synthesis (dialogue), provide an array of model IDs. **Multi-speaker is available with the S2 family (`s2-pro`, `s2.1-pro`, `s2.1…	nullable · default: null
prosody	ProsodyControl	Controls for adjusting the prosody (rhythm and intonation) of generated speech.	nullable
chunk_length	integer	Text segment size for processing.	100 ≤ n ≤ 300 · default: 300
normalize	boolean	Rewrites numbers, dates, units and symbols as spoken words before synthesis, improving stability. Uses `language` when it is set and otherwise detects the language of each text chunk.	default: true
language	string	BCP-47 language tag of the text, for example `en`, `es-MX` or `zh-CN`. Case-insensitive, and `_` is read as `-`. Used only by text normalization (how numbers, dates, units and symbols are spelled out before synthesis) and by word-timestamp alignment. It is not passed to the speech model and does not change the voice, accent or audio quality; a wrong tag only changes how those tokens are spelled out. Omit it, or send `auto` or an empty string, to detect the language per chunk. A tag without dedicated normalization rules skips normalization instead of failing. Without a region, Spanish follows Spain conventions; send `es-MX` for Mexican readings. When `normalize` is false it only affects word timestamps. For text that mixes languages, leave it unset.	length ≤ 35 · nullable
format	enum	Output audio format.	wav \| pcm \| mp3 \| opus · default: "mp3"
sample_rate	integer	Audio sample rate in Hz. When null, uses the format's default (44100 Hz for most formats, 48000 Hz for opus).	nullable
mp3_bitrate	enum	MP3 bitrate in kbps. Only applies when format is mp3.	64 \| 128 \| 192 · default: 128
opus_bitrate	enum	Opus bitrate in bps. -1000 for automatic. Only applies when format is opus.	-1000 \| 24000 \| 32000 \| 48000 \| 64000 · default: -1000
latency	enum	Latency-quality trade-off. normal: best quality, balanced: reduced latency, low: lowest latency.	low \| normal \| balanced · default: "normal"
max_new_tokens	integer	Maximum audio tokens to generate per text chunk.	default: 1024
repetition_penalty	number	Penalty for repeating audio patterns. Values above 1.0 reduce repetition.	default: 1.2
min_chunk_length	integer	Minimum characters before splitting into a new chunk.	0 ≤ n ≤ 100 · default: 50
condition_on_previous_chunks	boolean	Use previous audio as context for voice consistency.	default: true
early_stop_threshold	number	Early stopping threshold for batch processing.	0 ≤ n ≤ 1 · default: 1
features	string[]	Optional request-scoped TTS feature flags forwarded verbatim to the inference backend. Use ["quality-guard"] to enable the quality guard for this synthesis request. Feature availability is determined by the inference backend.	default: []
pronunciation_dictionary	PronunciationDictionaryRef[] \| PronunciationDictionaryInline[]	Optional list of up to 3 pronunciation dictionaries to apply during synthesis. Provide either references to platform-managed dictionaries OR inline literal dictionaries (the two forms are mutually exclusive in a single request). The server resolves and merges …	nullable · default: null

Types

5 $defs

PronunciationDictionaryInlineobject

Inline literal pronunciation dictionary. The server forwards the entries directly to the inference engine without contacting the platform.

items*

PronunciationItem[]

Replacement entries for this dictionary. See the top-level `pronunciation_dictionary` field description for replacement semantics.

items ≤ 5000

PronunciationDictionaryRefobject

Reference to a server-managed pronunciation dictionary. The server resolves contents via the platform pronunciation-dictionaries API and forwards the full merged dictionary to the inference engine, which performs the substitution.

id*	string	Dictionary identifier as registered on the platform.
version*	string	Immutable version identifier for the dictionary. Version is required — there is no implicit `latest`.

PronunciationItemobject

A single key/value entry in a pronunciation dictionary. The inference engine replaces every occurrence of `key` in the request text with `value` during synthesis. With the default `type: "phoneme"` the value is spoken as a phonetic form; with `type: "alias"` i…

key*	string	Source substring to match. Pure substring match — no tokenization, no regex. Overlapping matches resolve leftmost-longest. For CJK text include enough context to disambiguate. For `type: "alias"` the key must not start or end with whitespace and must not conta…	length ≥ 1 · length ≤ 256
value*	string	Replacement for the key during synthesis. For `type: "phoneme"` this is a phonetic representation; dictionary authors should NOT include the `<\|phoneme_start\|>` / `<\|phoneme_end\|>` markers themselves, because the inference engine wraps the value with those mar…	length ≥ 1 · length ≤ 1024
type	enum	How `value` replaces `key`. `phoneme` (default) speaks the value as a phonetic form. `alias` substitutes the literal text, which then goes through the same text normalization as the rest of the request. Omitted or `null` means `phoneme`, so existing dictionari…	phoneme \| alias · default: "phoneme"
case_sensitive	boolean	When true the match is case-sensitive; when false ASCII case folding is applied.	default: false

ProsodyControlobject

Controls for adjusting the prosody (rhythm and intonation) of generated speech.

speed	number	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.	default: 1
volume	number	Volume adjustment in decibels (dB). 0 = no change, positive values = louder, negative values = quieter.	default: 0
normalize_loudness	boolean	Normalize output loudness for more consistent perceived volume. Applies to the S2 family (`s2-pro`, `s2.1-pro`, `s2.1-pro-free`); on `s1` it is accepted but has no effect.	default: true

ReferenceAudioobject

A voice sample with its transcript, used for zero-shot voice cloning. The model will attempt to match the voice characteristics from the audio sample.

audio*	string	Raw audio bytes of the voice sample. Supported formats: WAV, MP3, FLAC. For best results, use 10-30 seconds of clear speech with minimal background noise.	format: binary
text*	string	The exact transcript of what is spoken in the audio sample. Accuracy is important for voice cloning quality.

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", …}]}