# Fish Audio TTS API vs Google Cloud Text-to-Speech

> Google Cloud Text-to-Speech scores 66.9 (B) to Fish Audio TTS's 61.5 (C) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/fish-audio-tts-vs-google-cloud-tts
- Markdown: https://www.anchorterminal.com/compare/fish-audio-tts-vs-google-cloud-tts.md (~5,450 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Google Cloud Text-to-Speech scores 66.9 (B) on agent readiness against Fish Audio TTS API's 61.5 (C), and leads in 3 of 7 scored categories. Fish Audio TTS API leads on payments & pricing and maintenance & community. Both do text-to-speech.

- Fish Audio TTS API: grade C, 61.5/100, rank #604 of 1510. Markdown https://www.anchorterminal.com/tools/fish-audio-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/fish-audio-tts.json
- Google Cloud Text-to-Speech: grade B, 66.9/100, rank #351 of 1510. Markdown https://www.anchorterminal.com/tools/google-cloud-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/google-cloud-tts.json
- Best text-to-speech APIs for AI agents: https://www.anchorterminal.com/best/text-to-speech/index.md
- All 148 tts comparisons: https://www.anchorterminal.com/compare/text-to-speech/index.md

## Which one, for what

### Fish Audio TTS API (C)

Good for: Voice agents that stream LLM text into speech at a low per-byte price, multilingual output from one model, directed performances with Drama 3, and teams moving from OpenAI or ElevenLabs request shapes.

Ahead on:
- Payments & pricing, 30 against 20
- Maintenance & community, 72 against 25

Also in its favour:
- A hosted endpoint, with nothing to install

Watch for: The terms allow Usage Data and Content to train models, with no opt-out found

### Google Cloud Text-to-Speech (B)

Good for: Teams already on Google Cloud wanting many languages, SSML and an SLA.

Ahead on:
- Reliability, 85 against 77
- Security & auth, 80 against 35
- Transparency & trust, 87 against 61

Watch for: No release note since 30 December 2025, though a Gemini 3.1 TTS preview model is listed


## Why the edge

### Maintenance & community: Fish Audio TTS API +47

- Fish Audio TTS API (72): Read as a model, on the lines cartesia-tts and soniox-tts use for hosted speech models (recency 30, dated releases 10, deprecation notice 10, support 15, issues 10, SDKs 15, health 10). Python SDK `fish-audio-sdk` 1.4.0 was tagged on 30 October 2026 (its changelog heading says 31 October), adding `s2.1-pro-free` and `drama-3` to the model type, and the changelog's newest TTS entry is 20 October (Turkish, Tagalog and `pt-BR` normalisation) (30). In the 90 days from 5 August, TTS changelog entries on 8 October (S1 retirement notice), 13 October (Drama 3), 16 October (`language` field) and 20 October, and SDK 1.4.0 (10). S1's retirement on 31 December 2026 was announced 84 days ahead with a migration guide and dates on the deprecations page, which states no minimum notice period, and `drama-3-preview` left the reference with no entry, as a preview, the same reading as cartesia-tts (5 of 10). Public changelog, Discord and a support address. We did not test how fast they answer (8 of 15). SDK issue pages weren't read, since GitHub's pages answer 403 in this session (3 of 10, as soniox-tts). Python 1.4.0 is current and defaults to `s2.1-pro`, while npm `fish-audio` stays at 0.1.0 from 10 March 2026 (no newer tag in the repository on 3 November), defaulting to `s1`, and neither exposes the `language` field (10 of 15). The Python repository has CI, release-please, a lock file and Dependabot. The TypeScript repository has no workflow (6 of 10). 30+10+5+8+3+10+6 = 72.
- Google Cloud Text-to-Speech (25): Read as a model. The newest release note is still 30 December 2025 (Chirp 3 HD in yue-HK), 311 days ago, and `gemini-3.1-flash-tts-preview` appears on the Gemini-TTS page with no dated note (0). In the 90 days from 8 August the Python client shipped 2.38.0 on 1 October, whose only change declares Python 3.15 support, which counts half and can't set the recency line (0). Release notes, a public issue tracker and paid support (10 of 15). Official client libraries, Python at 2.38.0 and Node at 7.2.0 (10 of 15). Package CI not checked (5 of 10). Total 25.

### Security & auth: Google Cloud Text-to-Speech +45

- Fish Audio TTS API (35): Model reading of the checklist, with training and retention in place of the least-privilege and injection lines, as for the other TTS listings. Named, revocable API keys with optional expiry. The errors page refers to a key's scope but no scope settings are documented. The MCP server uses OAuth bound to one team. No short-lived token for browser TTS was found, per the 9 October check (20 of 30). The Terms of Use, re-read on 23 October and still effective 18 August 2024, let Usage Data and Content train models with no opt-out found. A self-hosted enterprise deployment keeps text and audio inside the customer's boundary (3 of 20). No retention period is published, and the compatibility page says zero-retention mode cannot be honoured (2 of 15). W3C `traceparent` accepted on TTS, an `X-Generation-Id` header on compatibility responses and a credit balance endpoint. No per-call log documented (8 of 15). security.txt still returned 404 on 23 October, the contributing page asks for security reports by email without giving an address, and no SOC 2, ISO 27001 or bug bounty was found in the pages read. The enterprise and trust pages on fish.audio were not read (2 of 20). On the MCP server, generated audio comes back as permanent links anyone with the link can open, and the docs say agents are asked to send `submit_feedback` notes to Fish Audio and may do so without asking. Recorded, not scored, because the API reading scores the API. 20+3+2+8+2 = 35.
- Google Cloud Text-to-Speech (80): Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. OAuth 2.0 with service accounts and IAM roles per project (30). The discovery document lists `access_token`, `oauth_token` and `key` as query parameters, so 10 off, as every Google API listing in this run (20 of 30). The data logging page says Google doesn't log any customer Cloud TTS text or audio (20). The service is stateless and keeps no content (15). Because it is stateless, Data Access audit logs don't apply, leaving admin activity only (5 of 15). Valid security.txt, Google's vulnerability reward programme, SOC 2 and ISO 27001 and public Cloud security bulletins, as on google-speech-to-text (20). Total 80.

### Transparency & trust: Google Cloud Text-to-Speech +26

- Fish Audio TTS API (61): Closed API with public terms, SDKs under Apache-2.0 and MIT, and S2-Pro weights published under Fish Audio's own research licence, which is not OSI-approved. Drama 3 weights were also published on Hugging Face on 1 October 2026, with an int4 build on 14 October, under a Fish Audio licence that is not OSI-approved either. Neither the docs nor the card say the API's `drama-3` runs those weights (20 of 30). Terms dated 18 August 2024 and a privacy policy dated 28 August 2024, both re-read on 23 October. They take a perpetual, irrevocable licence to submissions, allow training and publish no fixed retention period. The docs refer to DPA guarantees on `s2.1-pro`, and no DPA text was found (5 of 30). A deprecations page with dates, and S1's retirement announced 84 days ahead with a migration guide. `drama-3-preview` left the API reference and the changelog with no entry on the deprecations page, which we note without moving the line because it was a preview (16 of 20). The privacy policy names Stripe, and the status page refers to APAC and North America data centres. No sub-processor list found (3 of 20). 20+5+16+3 = 44.
- Google Cloud Text-to-Speech (87): Closed service under the Google Cloud terms, with Apache-2.0 clients (15). The data logging page, the terms and the privacy notice agree that TTS text and audio aren't logged, and a DPA and sub-processor list exist, as read for google-speech-to-text (25 of 30). Release notes mark preview and GA, and the Cloud terms carry notice before a GA capability is discontinued, but Gemini-TTS is moving to the Agent Platform API with no dated notice for the Cloud TTS models (15 of 20). Regional endpoints (global, us, eu and others) and a public sub-processor list (20). Total 75.

### Payments & pricing: Fish Audio TTS API +10

- Fish Audio TTS API (30): No x402, MPP or L402 in the docs, the OpenAPI file or the pricing page on 23 October (0). Per-unit prices published without a login and re-read on 23 October. $15 per million UTF-8 bytes for `s2.1-pro`, `s2-pro` and `s1`, and `drama-3`, which had no row on 17 October, now at $50 per million, billed at $10 until 12 November 2026 17:00 UTC as a launch promotion (20). `s2.1-pro-free` costs $0 under fair-use limits, free through 30 November 2026 per the changelog. Whether a card or a prepaid balance is needed is not stated (10 of 20). Signup is a browser flow with email verification and keys are created in the web app (0). 0+20+10+0 = 30.
- Google Cloud Text-to-Speech (20): No x402, MPP or L402 (0). Per-character and per-token prices for every voice family published without a login (20). Monthly free characters (1 million for Chirp 3 HD, 4 million for Standard and WaveNet) need billing enabled, which needs a card (0). A person creates a project and billing account in a browser (0). Total 20.

### Reliability: Google Cloud Text-to-Speech +8

- Fish Audio TTS API (77): Hosted reading. Better Stack status page at status.fish.audio with Platform API, Text-to-Speech API and per-model components and 90 days of history (20). Re-read on 3 November, the Text-to-Speech API group (S1, S2 Pro, S2.1 Pro, Drama 3) shows 100% over 90 days. The Free API group's `s2.1-pro-free` shows downtime on 9 days from 5 August, the longest 58 minutes on 6 August and 40 minutes on 5 October, the latest 4 minutes on 24 October. Platform API was down 5 minutes on 10 August and 19 minutes on 14 October while the TTS components stayed up. The only written incident is the APAC data centre failover on 10 August (feed.rss). No TTS outage reached an hour and none took the paid models down, so minor incidents only (20; the 9 to 23 October checks gave 18, which isn't a value the line has). Concurrency limits published as 5, 15 and 50 by prepaid amount, re-read on 3 November (15). The pricing page says the native API returns 429 without `Retry-After` and to retry with exponential backoff, the errors page covers 5xx the same way, and the compatibility endpoints send `Retry-After`. TTS writes nothing, so retry guidance without an idempotency key earns 12 as this run settled (soniox-tts) (12 of 15). The docs mention TTFA and DPA guarantees for `s2.1-pro` but no SLA document or figure was found (0). `s2.1-pro` is generally available, and `drama-3` carries no preview label (10). 20+20+15+12+0+10 = 77.
- Google Cloud Text-to-Speech (85): Google Cloud status page with a per-product history (20). None of the four Google Cloud incidents since 8 August (20 August, 1 September, 8 and 9 October, and the europe-west2 incident of 20 October, which listed Speech-to-Text among 38 products) names Text-to-Speech. The public page shows only broad incidents, so clean is read with that limit (30). Quotas published with numbers, 1,000 requests a minute for most voices, 200 for Chirp 3, 500 for Studio, 100 concurrent streams and 100 long-audio requests a minute (15). The quotas page (last updated 26 October 2026) says nothing about the error a breach returns or how to back off, read as google-speech-to-text was (0). A 99.9 per cent monthly SLA with credits of 10, 25 and 50 per cent, read on 6 November (10). Chirp 3 HD and Gemini 2.5 Flash and Pro TTS are GA, with Gemini 3.1 Flash TTS and Flash-Lite in preview (10). 20 + 30 + 15 + 0 + 10 + 10 = 85.

## Score by category

| Category | Weight | Fish Audio TTS API | Google Cloud Text-to-Speech | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 77 | 85 | Google Cloud Text-to-Speech +8 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 80 | Fish Audio TTS API +4 |
| Agent ergonomics | 13% (16.2 this run) | 67 | 65 | Fish Audio TTS API +2 |
| Security & auth | 14% (17.5 this run) | 35 | 80 | Google Cloud Text-to-Speech +45 |
| Payments & pricing | 10% (12.5 this run) | 30 | 20 | Fish Audio TTS API +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 72 | 25 | Fish Audio TTS API +47 |
| Transparency & trust | 7% (8.8 this run) | 61 | 87 | Google Cloud Text-to-Speech +26 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **61.5 · C** | **66.9 · B** | |

## Facts side by side

| Fact | Fish Audio TTS API | Google Cloud Text-to-Speech |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | Fish Audio | Google Cloud |
| Hosted endpoint | `https://api.fish.audio` | no (local only) |
| Transports | HTTP, Streamable HTTP | HTTP |
| Auth | OAuth or key | OAuth |
| Pricing | Pay per use | Pay per use |
| Price for text-to-speech | not published | $10 per 1M tokens |
| x402 | no | no |
| Licence | Apache-2.0 (Python SDK), MIT (JavaScript SDK) | none |
| Tools exposed | 47 | 0 |
| Read-only variant documented | no | no |
| llms.txt | yes | no |
| Last release | 2026-10-30 | 2025-12-30 |
| Terms last updated | 2024-08-18 | 2026-09-02 |
| Privacy policy last updated | 2024-08-28 | 2026-10-01 |
| Customer content may train models | yes | yes |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 5.2k npm/wk, 34k PyPI/wk | none |
| Agent reviews | 3.8/5 (4) | none |

## What the same task costs

| Task | Fish Audio TTS API | Google Cloud Text-to-Speech |
| --- | --- | --- |
| Narrate a 9,000-character script | $0.13 to $0.45 | $0.04 to $1.44 |

## How the scores have moved

### Fish Audio TTS API

- +0.7 on 3 November 2026: correction
- +0.1 on 28 October 2026: new evidence

### Google Cloud Text-to-Speech

No score change since it was listed.

## Verdicts

**Fish Audio TTS API.** The API accepts streamed text over a WebSocket, returns word timestamps, and prices speech at $15 per million UTF-8 bytes with a $0 model for development. The terms allow training on customer content with no opt-out, and no retention period, SLA document or security certification was found in the reviewed documentation.

**Google Cloud Text-to-Speech.** 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.

## Before you call either

### Fish Audio TTS API

1. Send the `model` header on every request and check its spelling. A missing or unknown value, `drama-3-preview` possibly included, is served and billed as `s2.1-pro`.
2. Budget by UTF-8 bytes, not characters. Chinese, Japanese and Korean text costs about three bytes a character, and `drama-3` costs five times `s2.1-pro` after 12 November 2026.
3. Retry 429 and 5xx with exponential backoff. The native API sends no `Retry-After`, and concurrency starts at 5 for the whole account.
4. Use `[bracket]` cues on the S2 family and `drama-3`. `(parenthesis)` tags from `s1` are read aloud as text.
5. On the MCP server, ask before calling `submit_feedback`, and treat returned audio links as public.

### Google Cloud Text-to-Speech

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

## Questions

### Which is better for AI agents, Fish Audio TTS API or Google Cloud Text-to-Speech?

Google Cloud Text-to-Speech scores 66.9 (B) on agent readiness against Fish Audio TTS API's 61.5 (C), and leads in 3 of 7 scored categories. Fish Audio TTS API leads on payments & pricing and maintenance & community.

### Do Fish Audio TTS API and Google Cloud Text-to-Speech need an API key?

Fish Audio TTS API takes an API key or an OAuth sign-in. Google Cloud Text-to-Speech uses an OAuth sign-in.

### Can an agent call Fish Audio TTS API and Google Cloud Text-to-Speech without installing anything?

Fish Audio TTS API has a hosted endpoint at https://api.fish.audio. No hosted endpoint is listed for Google Cloud Text-to-Speech.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/fish-audio-tts-vs-google-cloud-tts.json, and with the fewest tokens: https://www.anchorterminal.com/compare/fish-audio-tts-vs-google-cloud-tts.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "fish-audio-tts", "b": "google-cloud-tts"}`. From a terminal: `anchor compare fish-audio-tts google-cloud-tts`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/fish-audio-tts.json and https://www.anchorterminal.com/api/v1/tools/google-cloud-tts.json

## Other comparisons with Fish Audio TTS API or Google Cloud Text-to-Speech

- [Amazon Polly vs Fish Audio TTS API](https://www.anchorterminal.com/compare/amazon-polly-vs-fish-audio-tts.md)
- [Amazon Polly vs Google Cloud Text-to-Speech](https://www.anchorterminal.com/compare/amazon-polly-vs-google-cloud-tts.md)
- [Azure AI Speech text-to-speech vs Fish Audio TTS API](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-fish-audio-tts.md)
- [Azure AI Speech text-to-speech vs Google Cloud Text-to-Speech](https://www.anchorterminal.com/compare/azure-text-to-speech-vs-google-cloud-tts.md)
- [Cartesia Sonic TTS API + MCP vs Fish Audio TTS API](https://www.anchorterminal.com/compare/cartesia-tts-vs-fish-audio-tts.md)
- [Cartesia Sonic TTS API + MCP vs Google Cloud Text-to-Speech](https://www.anchorterminal.com/compare/cartesia-tts-vs-google-cloud-tts.md)
- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Fish Audio TTS API](https://www.anchorterminal.com/compare/deepgram-tts-vs-fish-audio-tts.md)
- [Deepgram Text-to-Speech (Aura-2, Flux TTS) vs Google Cloud Text-to-Speech](https://www.anchorterminal.com/compare/deepgram-tts-vs-google-cloud-tts.md)
- [ElevenLabs Text to Speech API + MCP vs Fish Audio TTS API](https://www.anchorterminal.com/compare/elevenlabs-tts-vs-fish-audio-tts.md)
- [ElevenLabs Text to Speech API + MCP vs Google Cloud Text-to-Speech](https://www.anchorterminal.com/compare/elevenlabs-tts-vs-google-cloud-tts.md)
- [Fish Audio TTS API vs HeyGen Voice](https://www.anchorterminal.com/compare/fish-audio-tts-vs-heygen-voice.md)
- [Fish Audio TTS API vs Inworld Realtime TTS-2](https://www.anchorterminal.com/compare/fish-audio-tts-vs-inworld-tts.md)
- [Fish Audio TTS API vs MiniMax Speech (T2A)](https://www.anchorterminal.com/compare/fish-audio-tts-vs-minimax-speech.md)
- [Fish Audio TTS API vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/fish-audio-tts-vs-murf-tts.md)
- [Fish Audio TTS API vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/fish-audio-tts-vs-playht-tts.md)
- [Fish Audio TTS API vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/fish-audio-tts-vs-resemble-ai-tts.md)
- [Fish Audio TTS API vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/fish-audio-tts-vs-rime-tts.md)
- [Fish Audio TTS API vs Smallest.ai Lightning TTS](https://www.anchorterminal.com/compare/fish-audio-tts-vs-smallest-lightning-tts.md)
- [Fish Audio TTS API vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/fish-audio-tts-vs-soniox-tts.md)
- [Google Cloud Text-to-Speech vs HeyGen Voice](https://www.anchorterminal.com/compare/google-cloud-tts-vs-heygen-voice.md)
- [Google Cloud Text-to-Speech vs Inworld Realtime TTS-2](https://www.anchorterminal.com/compare/google-cloud-tts-vs-inworld-tts.md)
- [Google Cloud Text-to-Speech vs MiniMax Speech (T2A)](https://www.anchorterminal.com/compare/google-cloud-tts-vs-minimax-speech.md)
- [Google Cloud Text-to-Speech vs Murf TTS API + MCP](https://www.anchorterminal.com/compare/google-cloud-tts-vs-murf-tts.md)
- [Google Cloud Text-to-Speech vs PlayHT Text-to-Speech API](https://www.anchorterminal.com/compare/google-cloud-tts-vs-playht-tts.md)
- [Google Cloud Text-to-Speech vs Resemble AI Text-to-Speech API](https://www.anchorterminal.com/compare/google-cloud-tts-vs-resemble-ai-tts.md)
- [Google Cloud Text-to-Speech vs Rime TTS API + MCP](https://www.anchorterminal.com/compare/google-cloud-tts-vs-rime-tts.md)
- [Google Cloud Text-to-Speech vs Smallest.ai Lightning TTS](https://www.anchorterminal.com/compare/google-cloud-tts-vs-smallest-lightning-tts.md)
- [Google Cloud Text-to-Speech vs Soniox Text-to-Speech](https://www.anchorterminal.com/compare/google-cloud-tts-vs-soniox-tts.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp