Intelligence · Component · reader-tts
Streaming article text-to-speech
What it does
Read bilingual article text with realtime PCM streaming, configurable voices, cached audio and system-voice fallback.
Core pattern
Bilingual text narration + caching and audio fallback
- Input
- Article text
- Output
- Audio stream and playback state
Key parameters
| Name | Type | Default | Values |
|---|---|---|---|
| text | string | — | — |
| language | string | en | — |
| speech_rate | number | 1 | 0.25–4 |
| chunk_chars | integer | 500 | 20–10000 |
| sample_rate_hz | integer | 24000 | 8000–192000 |
Maturity and limits
WebSocket audio protocol client and dedicated TTS verification scripts. Source paths were inspected statically; tests and live integrations were not executed. This rating describes implemented code, not production validation.
No root reuse license found; publisher content and sports data need reuse rights; Credential-bearing configuration is excluded from this inventory.
Used in pipelines
Not part of a pipeline yet; available as a standalone component.
Industry tags
- Media & contentSource-supported industry
For work involving editorial material, programs and reader services, use bilingual text narration followed by caching and audio fallback.
- HealthcareTransferable use
For organizing consented appointment-service interviews, use bilingual text narration followed by caching and audio fallback.
Skills pack
Contract scaffold and deterministic mock
Download · 10KBSHA-256 71a1e2803b2780668994830e806b80a5ea56ab6a21942047580d2a5ea95bd783
Related components
-
Long-audio transcription, overlap alignment and speaker stitching
Long audio chunk transcription + seam alignment and timestamps
Working 1 pipeline -
Court calibration and reviewed trajectory reconstruction
Human trajectory annotation correction + calibration reuse and revision audit
Working 1 pipeline -
Ad-aware podcast transcript alignment
Audio fingerprint matching + cross-copy time offsets
Working 1 pipeline