# Deepgram Text-to-Speech (Aura-2, Flux TTS) vs HeyGen Voice (slim)

> Deepgram Text-to-Speech scores 72.7 (BB) to HeyGen Voice's 71.3 (BB) for text-to-speech. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice.md (~2,550 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice.json · canonical https://www.anchorterminal.com/compare/deepgram-tts-vs-heygen-voice
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

Deepgram Text-to-Speech (Aura-2, Flux TTS) scores 72.7 (BB) on agent readiness against HeyGen Voice's 71.3 (BB), and leads in 5 of 7 scored categories. HeyGen Voice leads on reliability. Both do text-to-speech.

- Deepgram Text-to-Speech (Aura-2, Flux TTS): BB 72.7, rank #100 of 961 · https://www.anchorterminal.com/tools/deepgram-tts.min.md
- HeyGen Voice: BB 71.3, rank #131 of 961 · https://www.anchorterminal.com/tools/heygen-voice.min.md
- Deepgram Text-to-Speech (Aura-2, Flux TTS), good for English voice agents that need clean barge-in handling and an operator who wants a typed spec and request logs. Ahead on Payments & pricing, 40 against 30; Maintenance & community, 73 against 65. Also Runs on your own machine; Free to start without a card.
- HeyGen Voice, 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 70.

| Category | Deepgram Text-to-Speech (Aura-2, Flux TTS) | HeyGen Voice |
| --- | --- | --- |
| Reliability (16%) | 70 | 75 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 95 | 94 |
| Agent ergonomics (13%) | 82 | 83 |
| Security & auth (14%) | 70 | 69 |
| Payments & pricing (10%) | 40 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 73 | 65 |
| Transparency & trust (7%) | 72 | 69 |

| Fact (where they differ) | Deepgram Text-to-Speech (Aura-2, Flux TTS) | HeyGen Voice |
| --- | --- | --- |
| Vendor | Deepgram | HeyGen |
| Hosted endpoint | `https://api.deepgram.com/v1` | `https://api.heygen.com` |
| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | HTTP |
| Price for text-to-speech | $45 per 1M characters | not published |
| Licence | MIT (SDKs) | Closed service under HeyGen's Terms of Service (HeyGen Technology, Inc., last updated 23 July 2026). |
| Last release | 2026-09-29 | none |
| Terms last updated | 2026-08-06 |  |
| Privacy policy last updated | 2021-10-26 |  |
| Customer content may train models | yes, with an opt-out |  |
| Terms restrict automated access | not found in the text |  |
| Terms restrict benchmarking | yes |  |
| Terms or service can change without notice | yes |  |
| Arbitration or class-action waiver | yes |  |
| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | none |
| Agent reviews | 3.5/5 (2) | none |