What voice controls does Google document for Chirp 3: HD voices (pace, pause tags, SSML subset, punctuation) and where do they not apply?
Corrected 2026-10-24 - see C3-B955-10; the original statements below are kept for history and are superseded where the correction says so. Problem: control timing of Chirp 3 HD speech. Conditions: Google Cloud Text-to-Speech Chirp 3: HD voices. Method: pace via speaking_rate from 0.25 (very slow) to 2.0 (very fast), 1.0 unadjusted. Pause tags [pause short], [pause long] and [pause] work only in the markup input field, not the text field; their length is not fixed and adapts to context; the model may occasionally disregard them if placed unnaturally, and excessive use can cause problems. SSML subset (synchronous requests only; not for streaming): speak, say-as, p, s, phoneme, sub, break, audio, prosody and voice; tags not on that list are ignored. Punctuation guidance: periods = longer pause, commas = shorter, ellipses = longer deliberate pause, hyphens = brief pause; reading the script aloud before synthesising is advised. Use (inference): for exact timing use SSML break or post-edi...
Problem: control timing of Chirp 3 HD speech. Conditions: Google Cloud Text-to-Speech Chirp 3: HD voices. Method: pace via speaking_rate from 0.25 (very slow) to 2.0 (very fast), 1.0 unadjusted. Pause tags [pause short], [pause long] and [pause] work only in the markup input field, not the text field; their length is not fixed and adapts to context; the model may occasionally disregard them if placed unnaturally, and excessive use can cause problems. SSML subset (synchronous requests only; not for streaming): speak, say-as, p, s, phoneme, sub, break, audio, prosody and voice; tags not on that list are ignored. Punctuation guidance: periods = longer pause, commas = shorter, ellipses = longer deliberate pause, hyphens = brief pause; reading the script aloud before synthesising is advised. Use (inference): for exact timing use SSML break or post-edit silence; for natural beats use punctuation and pause tags; test per voice. Failure modes: pause tags in the text field are spoken or ignored (check); SSML ignored in streaming. Limitations: the page does not document emotion or style tags for Chirp 3 HD; page undated; round-1 gap note (Chirp tag support) is closed by this finding.
Curator correction 2026-10-24 (discovery audit record C3-B955-10; sources re-fetched 2026-10-24, excerpts re-located by curator GET): C3-B575-11 asks where Chirp 3 HD controls do not apply but omits that the SSML and voice-control sections are marked Preview (Pre-GA) and that pause control and custom pronunciation are not available in listed locales. C3-B664-05 recommends custom_pronunciations without the locale exclusions. Pace control is available in all locales.
Curator qualifications: All cited documentation excerpts located on the live pages by curator GET; no video sources.
Limitations: No emotion-style control documented; behaviour of ignored tags was not tested.
Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
"citations": [
{
"url": "https://cloud.google.com/text-to-speech/docs/chirp3-hd",
"note": "Pace control; Pause control; Pause control; Supported SSML elements"
}
]
}Evidence claims
- [sourced_fact] Curator correction 2026-10-24 (discovery audit record C3-B955-10; sources re-fetched 2026-10-24, excerpts re-located by curator GET): C3-B575-11 asks where Chirp 3 HD controls do not apply but omits that the SSML and voice-control sections are marked Preview (Pre-GA) and that pause control and custom pronunciation are not available in listed locales. C3-B664-05 recommends custom_pronunciations without the locale exclusions. Pace control is available in all locales. · locator: curator correction paragraph in this record body (C3-B955-10) source
- [sourced_fact] SUPERSEDED IN PART 2026-10-24 by curator correction C3-B955-10 (see the correction claim above); original kept for history: Problem: control timing of Chirp 3 HD speech. Conditions: Google Cloud Text-to-Speech Chirp 3: HD voices. Method: pace via speaking_rate from 0.25 (very slow) to 2.0 (very fast), 1.0 unadjusted. Pause tags [pause short], [pause long] and [pause] work only in the markup input field, not the text field; their length is not fixed and adapts to context; the model may occasionally disregard them if placed unnaturally, and excessive use can cause problems. SSML subset (synchronous requests only; not for streaming): speak, say-as, p, s, phoneme, sub, break, audio, prosody and voice; tags not on that list are ignored. Punctuation guidance: periods = longer pause, commas = shorter, ellipses = longer deliberate pause, hyphens = brief pause; reading the script aloud before synthesising is advised. Use (inference): for exact timing use SSML break or post-edit silence; for natural beats use punctuation and pause tags; test per voice. Failure modes: pause tags in the text field are spoken or ignored (check); SSML ignored in streaming. Limitations: the page does not document emotion or style tags for Chirp 3 HD; page undated; round-1 gap note (Chirp tag support) is closed by this finding. · locator: Pace control; Pause control; Pause control; Supported SSML elements source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |