# Google Cloud Text-to-Speech (slim)

> Google Cloud's Text-to-Speech API synthesises speech from text or SSML over REST and gRPC, with streaming, long-audio jobs, Chirp 3 HD voices, Gemini-TTS models steered by natural-language prompts, and older WaveNet, Neural2 and Standard voices.

- Full: https://www.anchorterminal.com/tools/google-cloud-tts.md (~8,200 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/google-cloud-tts.json · canonical https://www.anchorterminal.com/tools/google-cloud-tts
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07 · pricing https://www.anchorterminal.com/tools/google-cloud-tts#pricing · reviews https://www.anchorterminal.com/tools/google-cloud-tts#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**B · 66.9/100 · rank #350 of 1486 · #8 in Text-to-speech · not agent-ready · confidence medium**


Assessment: Cloud TTS has a typed discovery document, a 99.9 per cent SLA, no logging of text or audio, and voices from $4 to $160 per million characters. Its release notes stop at 30 December 2025, the newest Gemini TTS models ship only on the Agent Platform API, and tokens can travel in the URL.

## Facts

- Kind: Model API · vendor: Google Cloud · category: Text-to-speech · legal entity: Google LLC · provenance 98/100
- Local only (HTTP): pypi `google-cloud-texttospeech`, npm `@google-cloud/text-to-speech`
- Auth: OAuth · pricing: Pay per use · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Surface listed: The Cloud Text-to-Speech API at texttospeech.googleapis.com, read from docs.cloud.google.com (release notes, quotas, Gemini-TTS, Chirp 3 HD and data logging pages), the discovery document, cloud.google.com pricing and SLA pages and status.cloud.google.com on 6 November 2026. No project was made and no request was sent
- Voices: Chirp 3 HD, Gemini-TTS (single and multi-speaker, prompt-steered), Studio, Neural2, WaveNet, Standard and Polyglot (preview). Chirp 3 instant custom voice clones a voice at $60 per million characters
- Interfaces: `text:synthesize` (REST and gRPC), bidirectional streaming synthesis over gRPC, and `synthesizeLongAudio` as a long-running operation writing to Cloud Storage
- SSML: Supported on the classic voices, and on Chirp 3 HD since 17 October 2025 for `<phoneme>`, `<p>`, `<s>`, `<sub>` and `<say-as>`
- Same company: Google Cloud Speech-to-Text is listed as google-speech-to-text, and Gemini's own speech output through the Developer API is part of the gemini-api and gemini-live listings
- Prices: Chirp 3 HD voices $30 per 1M characters; Neural2 voices $16 per 1M characters; Standard and WaveNet voices $4 per 1M characters; Studio voices $160 per 1M characters; Gemini 2.5 Flash TTS audio output $10 per 1M tokens

- Scores: Reliability 85, Performance pending, Schema & documentation 80, Agent ergonomics 65, Security & auth 80, Payments & pricing 20, Task success pending, Maintenance & community 25, Transparency & trust 87 · total over the 7 assessed categories
- Why: Reliability, Google Cloud status page with a per-product history (20). · Schema & documentation, Discovery document revision 20260827 with typed methods and 26 schemas, and protocol buffers for gRPC (25). · Agent ergonomics, API reading of the checklist. · Security & auth, Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, Read as a model. · Transparency & trust, Closed service under the Google Cloud terms, with Apache-2.0 clients (15).
- Sources: 11, open questions: 3, both in the full twin
- Capabilities: speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages
- JSON: https://www.anchorterminal.com/api/v1/tools/google-cloud-tts.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/google-cloud-tts.svg` or a link to https://www.anchorterminal.com/tools/google-cloud-tts from a page on google.com or one of its subdomains, or the README at the root of github.com/googleapis/google-cloud-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: https://docs.cloud.google.com/text-to-speech/docs/getting-support; https://cloud.google.com/support; more in the full twin

## Before you call it

1. Send OAuth tokens in the Authorization header, never as `access_token` or `key` in the URL
2. Use `synthesizeLongAudio` with a Cloud Storage bucket for long text, and `text:synthesize` for short replies
3. Pick Chirp 3 HD for natural voices with SSML, and Gemini-TTS when the delivery needs prompt steering
4. Check whether the Gemini TTS model you want is on the Cloud TTS API or only on the Agent Platform API
5. Stay within 200 requests a minute on Chirp 3 voices, which have their own quota

## Connect

```bash
pip install google-cloud-texttospeech
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Polly | BB | 75.4 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/amazon-polly.min.md |
| ElevenLabs Text to Speech API + MCP | BB | 75.3 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/elevenlabs-tts.min.md |
| Azure AI Speech text-to-speech | BB | 71.5 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/azure-text-to-speech.min.md |
| Cartesia Sonic TTS API + MCP | C | 61.9 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/cartesia-tts.min.md |
| Inworld Realtime TTS-2 | C | 58.3 | speech.tts, speech.streaming, speech.voices, speech.ssml, speech.languages | https://www.anchorterminal.com/tools/inworld-tts.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)