speech-to-text

Soniox has released Soniox STT v6, the latest generation of its speech-to-text API. The model reads what a voice agent says while hearing the caller, and uses that text to recognize short replies and to drop the agent's own voice. It ships as stt-rt-v6 for streaming and stt-async-v6.

ElevenLabs has published details on Cue, a forced alignment model that sets character-level timing for every Scribe transcription. The company claims it beats every aligner it tested in all 29 benchmark languages and aligns an hour of audio in around half a second on its production GPU.

MarkTechPost published a coding guide that benchmarks Cactus Compute's 16.9 MB speech model, Cactus Whistle, against Whisper base on a CPU. The guide covers word error rate, speed, streaming latency, timestamps, keywords and speech-to-tool calls.

Mistral AI launched Voxtral 3, a speech family with two transcription models (Voxtral Small Transcribe 3 and Voxtral Mini Transcribe 3), a text-to-speech model (Voxtral Mini TTS 3) and a voice agent SDK. Transcription covers 50 languages, and the 4B-parameter Mini variant costs $0.0035 per minute. It is available through Mistral's EU-hosted API or for self-deployment.

IBM has released Granite-Switch-4.1-8B and Granite-Switch-4.1-30B, models that bundle a Decision adapter, a Guardian safety adapter and a speech-to-text model behind a single endpoint. IBM says the combined model uses roughly the same GPU VRAM as the base model alone. Benchmark claims are IBM's own, and context window and pricing were not disclosed.

Microsoft AI released MAI-Transcribe-2-Streaming, a real-time transcription model covering 60 languages with first partial results in just over 100 milliseconds. It also launched two text-to-speech models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, aimed at voice agents.

Meta Superintelligence Lab released Muse Voice Transcribe, its first real-time audio perception model, claiming state-of-the-art streaming speech-to-text with native speaker diarization. The model handles 20+ speakers and code-switching across languages, priced at $3 per 1,000 audio minutes.

Google has released Gemini 3.5 Transcribe, a speech-to-text model claiming a 4.0% word error rate in streaming mode and 2.6% in non-streaming mode, according to benchmarks from Artificial Analysis. The model already powers Gboard Rambler on Android and the Gemini app for macOS, with Chrome support coming next.

Amazon SageMaker AI has launched bidirectional streaming support for real-time inference, enabling WebSocket-based voice applications through vLLM integration. The feature uses HTTP/2 on port 8443 to bridge client connections with vLLM's Realtime API, allowing audio to stream in while transcription streams back simultaneously over a single persistent connection.

OpenAI has added three voice intelligence features to its Realtime API: GPT-Realtime-2 with GPT-5-class reasoning for complex conversational requests, GPT-Realtime-Translate supporting 70 input languages and 13 output languages, and GPT-Realtime-Whisper for live speech-to-text transcription. Translation and transcription are billed by the minute, while GPT-Realtime-2 uses token-based pricing.

Microsoft has released MAI-Transcribe-1, a speech-to-text model that achieves the lowest word error rate on the FLEURS benchmark across 25 languages, outperforming Whisper-large-V3, GPT-Transcribe, and Gemini 3.1 Flash-Lite. The model runs 2.5 times faster than Microsoft's previous Azure Fast offering and costs $0.36 per audio hour.

Hume AI has open-sourced TADA, a speech generation model that maps exactly one audio signal to each text token, achieving 5x faster processing than comparable systems. The model produced zero transcription hallucinations across 1,000+ test samples and runs on smartphones, available in 1B and 3B parameter versions under MIT license.

Artificial Analysis has released an updated speech-to-text benchmark showing ElevenLabs and Google as top performers. The benchmark provides comparative analysis of current speech recognition systems across multiple models.