Transcribe a live caller for a voice agent, with a clear end of turn
Four or more companies' docs show a full fit.
What counts as done
A final transcript event for each turn, with an explicit end-of-turn or finalisation signal, in a session that can last a 10-minute call.
Measured, for our own tests: the final event arrives within 500 ms of end of speech at the median, and no session silently stops returning text over a 10-minute call. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: transcribe what the caller is saying as they speak
, give me the final text when they stop talking
, wire speech-to-text into my phone agent
Does the job 6
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| AssemblyAI Speech-to-Text (Universal) B AssemblyAI, Inc. | Turn messages carry end_of_turn true; Terminate returns in-flight turns then Termination. Pipecat measured 282 to 307 ms median to final. acc-31's stall was on the retired v2 transcriber. source |
| Cartesia Ink B Cartesia AI, Inc. | Ink 2 emits turn.start, turn.eager_end, turn.resume and turn.end; close flushes remaining audio and returns a done acknowledgment. Pipecat measured 299 ms median, 1,584 ms at p99. source |
| ElevenLabs Scribe Speech to Text API BB Eleven Labs Inc. | committed_transcript is the final per segment; commit_strategy turn_prediction on scribe_v3_live commits when the model predicts the turn ended. Pipecat measured scribe_v2_realtime at 281 ms median. source |
| Inworld STT C Theai, Inc. dba Inworld AI | Finals carry isFinal true per turn with endOfTurnConfidenceThreshold and client endTurn; closeStream finalises pending audio. No independent latency row, and headers rather than query carry the key. source |
| Soniox Speech-to-Text B Soniox Inc. | enable_endpoint_detection finalises the segment and returns an <end> token; finalize forces a final. Pipecat measured stt-rt-v6 at 266 ms median; streams cap at 300 minutes. source |
| Speechmatics Speech-to-Text BB Cantab Research Ltd | Agent STT emits StartOfTurn and EndOfTurn, with AddSegment finals and EndOfStream then EndOfTranscript on close; Pipecat measured linden-1 at 369 ms median. Temporary keys travel in the WebSocket URL. source |
Does the job, with a limit 15
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Amazon Transcribe BB Amazon Web Services, Inc. | StartStreamTranscription returns segments with IsPartial false, but no end-of-turn event, and the Pipecat benchmark measured 1,136 ms median time to final, above the 500 ms target. source |
| Azure AI Speech speech-to-text BB Microsoft Corporation | Speech SDK recognized events are per-segment finals with no turn event; MAI-Transcribe-2-Streaming has no server VAD and needs a client commit. Pipecat measured 1,016 ms median to final. source |
| Deepgram Speech-to-Text (Nova-3, Flux) BB Deepgram, Inc. | Flux emits EndOfTurn with eot_threshold and eot_timeout_ms; Nova-3 streaming gives speech_final and CloseStream flushes. Pipecat measured Nova-3 at 247 ms, but acc-28 reports sessions silently stopping with no error. source |
| Giggy Speech to Text E Giggy | The live WebSocket returns cumulative transcription events with is_final and input_complete, but the docs say turn boundaries and VAD are the caller's job; no end-of-turn event and no independent latency row. source |
| Gladia Speech-to-Text API + MCP BB Gladia SAS | Live init has endpointing (silence seconds) and maximum_duration_without_endpointing, and receive_final_transcripts sends finals; no end-of-turn event beyond the final, and Gladia has no Pipecat latency row. source |
| Google Cloud Speech-to-Text B Google LLC | StreamingRecognize has SPEECH_ACTIVITY_END voice events and is_final results, but streams stop at 5 minutes and must be reopened; Pipecat measured latest-long at 878 ms and gemini-3.5-transcribe-live at 458 ms. source |
| IBM Watson Speech to Text C International Business Machines Corporation | The WebSocket returns final results per phrase with interim_results and end_of_phrase_silence_time, no explicit end-of-turn event, and the access token travels in the URL query string; no independent latency row. source |
| Mistral Voxtral Transcribe B Mistral AI (RCS Paris 952 418 325) | Realtime 2602 streams text deltas and a transcription.done event at the end, with no end-of-turn event; Pipecat measured it at 525 ms median. Realtime 3 (Public Preview) claims end-of-turn detection. source |
| Nemotron 3.5 ASR Streaming 0.6B C NVIDIA Corporation | Cache-aware streaming at 80 to 1,120 ms chunks; Pipecat measured 236 ms median to final, but the model emits text, not an end-of-turn event, so the caller supplies VAD and endpointing. source |
| OpenAI Speech to Text BB OpenAI OpCo, LLC | gpt-live-transcribe needs the client to commit each turn (no server_vad), then sends completed; acc-21 saw deltas arrive with the final. Pipecat measured gpt-4o-transcribe at 637 ms median. source |
| Qwen3-ASR-0.6B C Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check) | Streaming runs only through vLLM's realtime path, without timestamps or batching, and emits text rather than an end-of-turn event; no independent latency row. source |
| Qwen3-ASR-1.7B B Alibaba Cloud (the registrant of qwen.ai per RDAP, carried from the Qwen3.8-27B check) | Streaming runs only through vLLM's realtime path, without timestamps or batching, and emits text rather than an end-of-turn event; no independent latency row. source |
| Rev AI Speech-to-Text API C Rev.com, Inc. | Streaming returns partial and final hypotheses with no end-of-turn event, the access token travels in the URL query string, and Rev AI has no independent latency row. source |
| Smallest.ai Pulse STT B Smallest, Inc. | Live WebSocket has endpointing with eou_timeout_ms, is_final transcripts, speech_ended events and finalize and close_stream messages; Pipecat measured pulse at 398 ms median but 1,593 ms at p99, and keys may travel in the query string. source |
| Voxtral Mini 4B Realtime 2602 B Mistral AI (RCS Paris 952 418 325) | vLLM serves it on /v1/realtime with a 480 ms delay, but it emits text only, no end-of-turn event; Pipecat measured the hosted twin at 525 ms median and 1,913 ms at p99. source |
Doesn't do this job 8
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Cohere Transcribe 03-2026 C Cohere Inc. | Batch model with no streaming runtime or endpoint; Cohere's docs list audio-in text-out only. |
| Groq Speech-to-Text BB Groq LLC | No streaming or realtime endpoint; files or URLs only. |
| Ming-3.0-asr-tiny C inclusionAI, Ant Group (named in the site footer of inclusion-ai.org; the LICENSE copyright line reads inclusionAI) | Batch model; no streaming runtime, only SGLang-Omni server-sent events of a finished transcript. |
| Ming-3.0-audio-flash E inclusionAI, Ant Group (named in the inclusion-ai.org footer; no registered company named) | Offline audio-language model; no streaming transcription path is documented. |
| Ming-3.0-audio-tiny D inclusionAI (Ant Group) | Offline audio-language model; no streaming transcription documented. |
| MiniMax Speech-to-Text D Nanonoble Pte. Ltd. | Files only; stream=true streams text output of an uploaded file, with no live audio input. |
| Parakeet TDT 0.6B v3 B NVIDIA Corporation | An offline TDT model with no streaming runtime or end-of-turn signal; the speech.streaming tag is not supported by the card. |
| Underdog Bark 3.0 E Conway Research | Offline model run with Conway's loader; no streaming path. |
3 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- no streaming endpoint (Groq, Cohere Transcribe, Ming, Parakeet TDT without a streaming runtime)
- stream drops after 5 minutes without reconnect (Google 5-minute stream limit)
- session stops returning text with no error, as in acc-28 and acc-31
- credentials in the WebSocket query string where logs can keep them
Around it
Before: telephony.answer-call, voice.capture-microphone. After: llm.reply, text-to-speech.speak.
Where this comes from
Weight 18 of 100 in Speech-to-text: 6 of 32 accounts (acc-04, acc-21, acc-28, acc-29, acc-31, acc-11) plus two independent benchmarks built for this job alone; the use case vendors lead with
The same as data: /api/v1/use-cases/speech-to-text.voice-agent-live.json, or the MCP tool get_use_case with id speech-to-text.voice-agent-live. Other jobs in this category: /api/v1/niches?category=speech-to-text.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.