Skip to content
SPECIFICTION
Get listed

Lifegence Voiceprint API

github.com

APISelf-hosted
Visit github.com
Spec score 7.1 #17 of 22 in AI Voice Biometrics Software

What it is

Lifegence Voiceprint API is a free, open-source, self-hosted REST API for speaker verification and identification. Enrollment records a speaker’s voiceprint; verification compares audio with one enrolled speaker for 1:1 authentication, while identification searches enrolled speakers for a 1:N match. SpeechBrain ECAPA-TDNN produces 192-dimensional voice embeddings. The documented inputs are WAV, MP3, WebM, and OGG recordings lasting 3 to 30 seconds, with 5 to 10 seconds recommended. Docker Compose starts the API with PostgreSQL 16 and pgvector plus Redis 7. Requests use API keys in the X-API-Key header. Enrollment includes consent fields, and a delete endpoint removes associated voiceprint data. The security policy recommends TLS 1.3 in transit, encryption at rest, and treating embeddings as sensitive biometric information. Rate limits are 10 enrollment, 60 verification, and 30 identification requests per minute. The current version has no liveness or anti-spoofing controls and does not guarantee perfect recognition accuracy.

Spec sheet

Purpose
It is a self-hosted REST API for speaker verification (1:1) and identification (1:N).Read 8 Oct 2026 · github.com
Deployment
The project provides a Docker Compose quick start for running the API server.Read 4 Oct 2026 · github.com
Security
The security policy recommends TLS 1.3 in transit, encrypted database storage, API-key access control, and storing embeddings rather than raw audio.Read 8 Oct 2026 · github.com
License
The repository identifies the project as MIT licensed.Read 8 Oct 2026 · github.com
Accuracy limitation
The project warns that voice recognition does not guarantee 100% accuracy.Read 4 Oct 2026 · github.com
Audio input
Supported audio formats are WAV, MP3, WebM, and OGG, with durations from 3 to 30 seconds.Read 8 Oct 2026 · github.com
Authentication
Verification compares submitted audio against an enrolled speaker and returns a score and confidence level.Read 8 Oct 2026 · github.com
Biometric data
The security policy says embeddings should be treated as sensitive biometric data and calls for encryption at rest and TLS 1.3 in transit.Read 4 Oct 2026 · github.com
Client compatibility
The architecture documentation lists curl, Python, JavaScript, and mobile apps as clients.Read 8 Oct 2026 · github.com
Compliance note
The README says compliance with applicable laws, including GDPR and BIPA, is the user's responsibility.Read 8 Oct 2026 · github.com
Consent and deletion
Enrollment requires consent information, and the API provides an endpoint to delete a speaker and associated voiceprint data.Read 8 Oct 2026 · github.com
Enrollment
The API enrolls speakers by registering a voiceprint from an audio file.Read 8 Oct 2026 · github.com
Identification
Identification searches across speakers and can return up to 20 results.Read 8 Oct 2026 · github.com
Rate limits
The API specification lists limits of 10 enrollment, 60 verification, and 30 identification requests per minute.Read 8 Oct 2026 · github.com
Security limitation
The current version does not include liveness detection or anti-spoofing measures.Read 8 Oct 2026 · github.com
Storage stack
The documented stack includes PostgreSQL 16 with pgvector and Redis 7.Read 4 Oct 2026 · github.com
Technology
The project lists SpeechBrain ECAPA-TDNN with 192-dimensional embeddings, FastAPI, PostgreSQL with pgvector, Redis, and Docker Compose.Read 8 Oct 2026 · github.com
Verification
Its verification endpoint compares audio with an enrolled speaker for 1:1 authentication.Read 4 Oct 2026 · github.com
Voice model
The project uses SpeechBrain ECAPA-TDNN to produce 192-dimensional voice embeddings.Read 4 Oct 2026 · github.com
Vulnerability support
The security policy asks researchers to report vulnerabilities by email and lists acknowledgment within 24 hours.Read 4 Oct 2026 · github.com

Strong points and limits

Strong points

  • Free MIT-licensed open-source project
  • Supports verification and identification
  • Docker Compose deployment
  • Consent and deletion endpoints
  • Documented API rate limits

Limits

  • No liveness or anti-spoofing
  • Recognition is not guaranteed perfectly accurate
  • Users handle legal compliance
  • Requires self-hosted PostgreSQL and Redis stack

Who it suits

This API suits developers building self-hosted voice authentication or identification into web, Python, JavaScript, command-line, or mobile clients. Users must handle legal compliance, including applicable GDPR and BIPA duties.

Verdict

Lifegence provides a focused, self-hosted voiceprint API with clear endpoints and deployment components. Its biometric-security limitations and user-managed compliance obligations should be addressed before production use.

Where Specifiction places it

Alternatives to Lifegence Voiceprint APIAll alternatives →