Spex-TTS

Spec sheet

Purpose

Spex-TTS is a text-to-speech engine that grew out of a production live-translation product.Read 9 Oct 2026 · gandr.ai

Platforms

["web","api"]Read 20 Sep 2026 · gandr.ai

Free plan

YesRead 20 Sep 2026 · gandr.ai

Paid from

10Read 20 Sep 2026 · gandr.ai

Integrations

The maker documents API access through REST, server-sent events, and WebSocket; no named third-party integrations are listed on the opened API page.Read 9 Oct 2026 · gandr.ai

Privacy

Customer text and reference audio never enter a training set, according to the maker.Read 9 Oct 2026 · gandr.ai

Accuracy

The maker reports a 1.98% word error rate against a 2.17% human reference using the same scorer.Read 9 Oct 2026 · gandr.ai

API access

YesRead 20 Sep 2026 · gandr.ai

API limits

The maker says there is no voice-management API; a voice reference is sent in the request, and the API example uses a ten-second recording.Read 9 Oct 2026 · gandr.ai

Consent limit

The maker requires users to have the reference speaker’s consent but says consent is not detected by the service.Read 9 Oct 2026 · gandr.ai

Export formats

["WAV","raw PCM (pcm_s16le)"]Read 20 Sep 2026 · gandr.ai

Expression controls

Numeric controls and inline transcript tags can steer speech expression, including timed breaks and spelled-out text.Read 9 Oct 2026 · gandr.ai

Languages

23Read 20 Sep 2026 · gandr.ai

Languages

The maker says one cloned reference can be used across 23 languages.Read 9 Oct 2026 · gandr.ai

Performance

The maker reports first audio byte in 146 ms over the open internet and 116 ms p50 when the server is warm.Read 9 Oct 2026 · gandr.ai

Security claims

The maker’s site lists SOC 2 Type 2 infrastructure, HIPAA-Verified infrastructure, and GDPR-Ready infrastructure.Read 9 Oct 2026 · gandr.ai

Streaming

The API offers complete WAV responses, HTTP server-sent event streams, and WebSocket audio streams.Read 9 Oct 2026 · gandr.ai

Synthetic audio marking

Every generated sample carries an inaudible watermark that the maker says survives transcoding and cannot be skipped by configuration.Read 9 Oct 2026 · gandr.ai

Usage tracking

Usage is auditable per API key through GET /v1/usage.Read 9 Oct 2026 · gandr.ai

Voice cloning

The API supports instant voice cloning from ten seconds of a consenting speaker’s audio, and the clone speaks 23 languages.Read 9 Oct 2026 · gandr.ai

Plans and prices

Every Spex-TTS plan and price →

Where Specifiction places it

• Text-to-speech tools#34 of 2338.7
• Text-to-Speech Software#87 of 2238.3