# HeyGen Voice vs Smallest.ai Lightning TTS

> HeyGen Voice scores 73.6 (BB) to Smallest.ai Lightning TTS's 64.4 (B) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/heygen-voice-vs-smallest-lightning-tts
- Markdown: https://www.anchorterminal.com/compare/heygen-voice-vs-smallest-lightning-tts.md (~5,200 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

HeyGen Voice scores 73.6 (BB) on agent readiness against Smallest.ai Lightning TTS's 64.4 (B), and leads in 4 of 7 scored categories. Both do text-to-speech.

- HeyGen Voice: grade BB, 73.6/100, rank #102 of 1486. Markdown https://www.anchorterminal.com/tools/heygen-voice.md · JSON https://www.anchorterminal.com/api/v1/tools/heygen-voice.json
- Smallest.ai Lightning TTS: grade B, 64.4/100, rank #469 of 1486. Markdown https://www.anchorterminal.com/tools/smallest-lightning-tts.md · JSON https://www.anchorterminal.com/api/v1/tools/smallest-lightning-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

### HeyGen Voice (BB)

Good for: Speech in a voice cloned from one short recording, for agents that already make HeyGen videos or need a cloned narrator with streaming and timestamps.

Ahead on:
- Reliability, 75 against 58
- Schema & documentation, 97 against 92
- Agent ergonomics, 88 against 72
- Security & auth, 69 against 52

Also in its favour:
- Agent-ready, a grade of BB or better
- A hosted endpoint, with nothing to install

Watch for: 30 requests a minute per workspace member on the speech endpoints by default, and Turbo Free's shared capacity can return 429 below that

### Smallest.ai Lightning TTS (B)

Good for: Low-latency speech for voice agents, with English, Hindi code-switching and Indic voices.

Watch for: `lightning_v3.1`, the default model, retires on 30 November 2026 after a 2 November notice, and clones made on it stop working


## Why the edge

### Reliability: HeyGen Voice +17

- HeyGen Voice (75): Status page at status.heygen.com with components for www, app and api.heygen.com and dated incident history (20). It has no voice component. In the 90 days from 3 August, majors hit Video Agent (9 September, about 3.5 hours of 404s on new sessions) and Seedance (16 September, failures between 8:00 and 11:00 PST), and minors or no-impact incidents hit video workflows, video translation, sign-in (10 October) and general service speed (17 and 20 August). None names speech or voices, so partial and minor for this surface (20). The incidents feed and history feed list nothing after 10 October. The speech endpoints publish 30 requests a minute per workspace member (15). A 429 carries Retry-After and X-RateLimit headers, the docs ask for exponential backoff when it doesn't (as for a capacity 429), the OpenAPI file marks 502, 503 and 504 safe to retry, and voice creation and speech to speech take an Idempotency-Key (15). The terms disclaim uninterrupted service and no SLA was found, per the 10 October check (0). Instant voice creation is still in a preview, Turbo Free carries no availability guarantee, and the professional mode carries no label, so half (5). Total 75.
- Smallest.ai Lightning TTS (58): BetterStack status page at status.smallest.ai with components for the Global, India and USA APIs (one health check covers the Agents and Models APIs), docs, the app and Electron, and per-component history (20). In the 90 days from 8 August the health checks on the shared API failed in all three regions on 9, 10, 13, 14 and 15 September (about 8, 21, 33, 17 and 64 minutes of flapping), in the Global and India regions on 11 and 17 September (12 minutes each), and in the USA region alone on 1, 3, 5, 12, 21 and 30 September (6 to 62 minutes) and 6 October (12 minutes). Outages in every region at once are read as wide errors, so several majors (0). Limits are published with numbers but disagree. The limits page says one TTS request at a time per account with up to five sockets, the Lightning v3.1 Pro card says 10 concurrent and the pricing page says 15 streams and 100 requests a minute on pay as you go (8 of 15). 429 is documented with exponential backoff from 500 ms to 30 s and Retry-After when present, and the limits page tells clients to expect 429s at the concurrency ceiling (15). An infrastructure SLA of 99.99 per cent is named for Enterprise only, with no terms, and the terms disclaim any availability commitment (5 of 10). `lightning_v3.1_pro` is stable and only the dated checkpoint is preview (10). 20 + 0 + 8 + 15 + 5 + 10 = 58.

### Security & auth: HeyGen Voice +17

- HeyGen Voice (69): Model reading of the checklist, with training and retention in place of least-privilege and injection lines. API keys can be restricted to resource read and write scopes, a key without the scope gets 403 insufficient_api_key_scope, `GET /v3/api_keys/self` reports a key's scope mode, and the docs cover rotation (30). The privacy policy (11 August 2026) and the terms (23 July 2026) allow training on user input, with an opt-out by email, and the security page excludes enterprise data by default, per the 10 October check, not re-read on 1 November (10). No retention period for voices or speech was found, deleted data stays in backups for 60 days, and voices can be deleted through the API (5). Each response carries an X-Request-Id used in usage and billing records, and `end_user_id` attributes usage per end user. Audit logs of user and admin actions are for enterprise customers (10 of 15). A valid security.txt (expires 31 December 2026, re-read 1 November), a disclosure policy with safe harbour, SOC 2 Type II stated on the security page with reports on request, and no bug bounty. The report was not read, so the certification counts as a vendor claim (14 of 20). Total 69.
- Smallest.ai Lightning TTS (52): Model reading of the checklist, with training and retention in place of the least-privilege and injection lines. Plain `sk_` keys per organisation, shown once, revoked at once and deletable, with one key per environment advised. The docs say a key grants full account access, and no scope is offered. Short-lived access tokens (`wat_`, 30 to 900 seconds) cover only inference routes and can't mint tokens (22 of 30). The error reference documents the key as a `?token=` query parameter for browser WebSockets, and the token guide passes access tokens as `?api_key=` on the STT socket, so 10 off (12 of 30). The terms (21 October 2026) say Smallest won't use user content or input to train or improve its services. The privacy policy (18 September 2026) lists improving the services with machine learning as a use of usage data and doesn't address uploaded audio or text either way (15 of 20). Zero data retention and the `x-expire-content` header are Enterprise only, or a $1,000 a month HIPAA add-on on pay as you go. Other plans keep content readable in logs and the dashboard, with no retention period published (5 of 15). Usage is tracked per key, request rows sit in a dashboard log viewer, and every response carries `x-request-id`. No audit log of key actions was found (10 of 15). security.txt is valid to 31 December 2026 and the site footer claims SOC 2, GDPR and HIPAA compliance, while the pricing page lists SOC 2 compliance only on Enterprise. No bug bounty, disclosure policy or public advisories found (10 of 20). Total 52.

### Agent ergonomics: HeyGen Voice +16

- HeyGen Voice (88): API reading of the checklist. The completed response is a URL and a duration, streaming returns WAV parts as they are made, and timestamps come only when asked. Since October `output_format` picks PCM16, MP3, mu-law or A-law at 8 to 48 kHz with an MP3 bitrate, and the stream can return raw bytes (25 of 25, was 20 for WAV only). Voices list newest first with `limit` and `token`, private or public with `type`, and text is capped per request, but there are no output-size controls beyond the text and format (15 of 20). Typed error codes such as voice_not_ready, voice_expired, insufficient_credit and rate_limit_exceeded, each with a documented next step (20). Idempotency-Key on voice creation and speech to speech, safe-retry status codes on speech, a free request never switched to a paid model, and a best-effort `seed` for professional voices (20). Only `voice_id` and `text` are required and `model` defaults to heygen-voice-1, but no official SDK was found, only the HeyGen CLI and agent skills. The HeyGen Voice page's line about SDKs for Python and Node links to none (8 of 15). Total 88.
- Smallest.ai Lightning TTS (72): API reading of the checklist. Eight output formats, a choice of sample rate and word timestamps only when asked (22 of 25). Voices are listed per model and the docs say they filter by language and accent. Paging wasn't confirmed (14 of 20). Errors carry `error` and `message` fields with a shared status-code guide, without TTS-specific codes (14 of 20). Synthesis is stateless and `request_id` is echoed for correlation, but there is no idempotency key and billing of a retried request isn't stated (10 of 20). Two required fields, `text` and `voice_id`, but the default model retires on 30 November. Official Python and Node SDKs, with the Node SDK last published in May 2025 (12 of 15). Total 72.

### Schema & documentation: HeyGen Voice +5

- HeyGen Voice (97): OpenAPI 3.1 file at developers.heygen.com/openapi/external-api.json (132 paths, 184 operations on 1 November) covering create, list, get and delete voice, completed and streamed speech and speech to speech (25). llms.txt with a Markdown twin of every page (10). Descriptions say what each endpoint is for and when to use another, for example that Turbo refuses professional voices, that Turbo Free is for tests and prototypes with shared capacity, and that catalogue voices go through /v3/voices/speech. Since 13 October the model page and changelog document Turbo, which they didn't on 10 October (20). Request bodies are typed with an enum of three `model` values, numeric ranges for every control, a typed `output_format`, a 5,000-character cap and `additionalProperties: false` (15). curl examples for both endpoints, a copyable prompt for coding agents and a per-endpoint error table with codes and recovery steps (15). Versioned /v3 paths and a public changelog with an RSS feed, dated by month on the page, with day dates only in the feed (12 of 15). Total 97.
- Smallest.ai Lightning TTS (92): OpenAPI 3.1 for the sync and SSE routes and AsyncAPI 2.6 for the WebSocket, with request and event schemas (25). llms.txt and a Markdown copy of every page (10). A transport guide, model cards and the compare page say which model and transport suit which job, but changelog entries correct the language lists and enums the docs and spec carried (15 of 20). Typed fields with enums for model, sample rate, language and output format, an 8,000-character limit and pattern rules on `session_id` and `request_id` (14 of 15). Examples in curl, Python and JavaScript, with error bodies on the reference and a shared error page (13 of 15). Versioned `/v1` paths, a dated Lightning changelog and dated preview checkpoints (15). Total 92.

## Score by category

| Category | Weight | HeyGen Voice | Smallest.ai Lightning TTS | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 75 | 58 | HeyGen Voice +17 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 97 | 92 | HeyGen Voice +5 |
| Agent ergonomics | 13% (16.2 this run) | 88 | 72 | HeyGen Voice +16 |
| Security & auth | 14% (17.5 this run) | 69 | 52 | HeyGen Voice +17 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 65 | 68 | Smallest.ai Lightning TTS +3 |
| Transparency & trust | 7% (8.8 this run) | 66 | 70 | Smallest.ai Lightning TTS +4 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **73.6 · BB** | **64.4 · B** | |

## Facts side by side

| Fact | HeyGen Voice | Smallest.ai Lightning TTS |
| --- | --- | --- |
| Kind | Model API | Model API |
| Vendor | HeyGen | Smallest AI |
| Hosted endpoint | `https://api.heygen.com` | no (local only) |
| Transports | HTTP | HTTP, websocket |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Closed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026). | none |
| Tools exposed | none | 0 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-20 | 2026-11-02 |
| Terms last updated | 2026-07-23 | no date given |
| Privacy policy last updated | 2026-08-11 | no date given |
| Customer content may train models | yes | not found in the text |
| 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 | yes | yes |
| Arbitration or class-action waiver | yes | yes |
| Agent reviews | 3.5/5 (4) | none |

## What the same task costs

| Task | HeyGen Voice | Smallest.ai Lightning TTS |
| --- | --- | --- |
| Narrate a 9,000-character script | $0.13 to $0.27 | $0.16 to $0.18 |

## How the scores have moved

### HeyGen Voice

- +2.5 on 1 November 2026: pricing, product
- +0.2 on 27 October 2026: checklist
- -0.4 on 12 October 2026: new evidence

### Smallest.ai Lightning TTS

No score change since it was listed.

## Verdicts

**HeyGen Voice.** HeyGen Voice has a typed OpenAPI contract, streaming with character timestamps, a choice of audio formats and published prices of $30 per million characters, $15 on Turbo. Turbo Free costs nothing until 30 November 2026. Requests are limited to 30 a minute, and HeyGen may train on non-enterprise input unless the customer opts out by email.

**Smallest.ai Lightning TTS.** Lightning streams speech over HTTP, SSE or WebSocket with OpenAPI and AsyncAPI files and public prices of $0.175 to $0.195 per 10,000 characters. The default model retires on 30 November with 28 days' notice, published concurrency limits disagree, and the shared API failed in every region on five days in September.

## Before you call either

### HeyGen Voice

1. Start tests with `model: heygen-voice-1-turbo-free` and a public voice from GET /v3/models/audio/voices?type=public. It never falls back to a paid model
2. Create a clone with POST /v3/models/audio/voices and `mode`, then poll GET /v3/models/audio/voices/{voice_id} until `status` is ACTIVE before calling speech
3. Send `expressiveness_boost` only for instant voices. Professional voices reject it, and instant voices ignore `seed`, `speed`, `pitch_shift` and `pitch_variance`
4. On a 429 without Retry-After, back off exponentially. Capacity 429s carry no header
5. Use POST /v3/voices/speech for catalogue or designed voices. It is a different endpoint and price

### Smallest.ai Lightning TTS

1. Always send `"model": "lightning_v3.1_pro"`, since requests with no model go to a model that retires on 30 November 2026
2. Pick voices from `GET /waves/v1/lightning-v3.1-pro/get_voices`, because the v3.1 and v3.1 Pro catalogues differ
3. Keep each request under 8,000 characters and split longer text
4. Treat 429 as the concurrency ceiling and retry with backoff from 500 ms to 30 s, honouring Retry-After
5. Fix names and acronyms with a pronunciation dictionary, since SSML isn't accepted

## Questions

### Which is better for AI agents, HeyGen Voice or Smallest.ai Lightning TTS?

HeyGen Voice scores 73.6 (BB) on agent readiness against Smallest.ai Lightning TTS's 64.4 (B), and leads in 4 of 7 scored categories.

### Do HeyGen Voice and Smallest.ai Lightning TTS need an API key?

Both need an API key.

### Can an agent call HeyGen Voice and Smallest.ai Lightning TTS without installing anything?

HeyGen Voice has a hosted endpoint at https://api.heygen.com. No hosted endpoint is listed for Smallest.ai Lightning TTS.


## For agents

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

## Other comparisons with HeyGen Voice or Smallest.ai Lightning TTS

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