Free AI APIs for Speech creation

Real-time streaming via WebSockets with partial and committed transcripts, while Scribe v1 is positioned for high-accuracy file transcription rather than live use. ` Much lower latency, about 150 ms for Scribe v2 Realtime, versus Scribe v1 which is not optimized for real time. Both cover 99 languages. New control over segmentation with manual commit and built-in Voice Activity Detection, including tunable silence and sensitivity thresholds. Simpler client workflow with single-use tokens and SDKs for microphone streaming or server-side chunking. Broader live-ingest support, including PCM at 8–48 kHz and μ-law, suitable for telephony and varied capture pipelines. Updated pricing and limits called out separately for Scribe v2 Realtime, plus distinct concurrency guidance, whereas Scribe v1 has its own concurrency rules.

2