Shotcraft
Voice and speech

Chirp 3: HD voices (Google Cloud Text-to-Speech)

Google Cloud's current-generation HD voice set, with 28 voices available across 50+ languages and locales.

A speech model by Google · read 2026-08-14 · sourcing high

Weights
Not released
API
Yes
Commercial use
Not established

It supports pace control from 0.25x to 2x, pause markup tags, custom pronunciations via IPA or X-SAMPA, and both streaming and batch synthesis. SSML is supported for synchronous requests but not for streaming.

Commercial use — Not established

The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.

  • Requires consent from the person depicted. Instant Custom Voice is the cloning path and is priced separately at $60/1M characters; consent requirements for custom voice creation were not documented on the pages fetched

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Google's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
text
What it makes
audio
Controls
speed-control, pronunciation-dictionary, streaming-low-latency
Weights
Not released
API
Yes
Pricing
$30 per 1M characters (US$0.00003 per character), with the first 1M characters per month free. For comparison on the same page: Standard and WaveNet $4/1M (4M free), Neural2 $16/1M (1M free), Studio $160/1M (1M free), Instant Custom Voice $60/1M with no free tier.
Released or updated
not established
Languages
50, not individually listed by the vendor

Strengths

  • 50+ languages and locales, GA in six Google Cloud regions
  • Pause markup and IPA/X-SAMPA pronunciation control
  • Streaming and batch synthesis
  • Predictable per-character pricing with a 1M/month free tier

Weaknesses

  • Only 28 voices, far fewer than ElevenLabs or Azure
  • No SSML on streaming requests
  • No emotion or style prompting documented
  • Character limit per request not documented
  • Two locales (Punjabi-India, Chinese-Hong Kong) still in Preview

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Google

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Gemini native TTS

Speech generation built into Gemini models, driven by natural-language style instructions rather than SSML. It offers 30 voice options across 60+ auto

Voice and speech

Azure AI Speech text-to-speech (Neural, Neural HD, MAI voices)

Microsoft's enterprise speech synthesis service, with 200+ prebuilt neural voices across 80+ locales plus tiers for HD voices, multilingual voices, mu

Voice and speech

Sonic 3.5

Cartesia's current TTS model, documented at sub-90ms first-byte latency across 42 languages. It is tuned for conversational delivery and for reading a

Voice and speech

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.