> ## Documentation Index > Fetch the complete documentation index at: https://polargrid.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Kokoro 82M > Low-latency preset-voice streaming TTS on PolarGrid edge nodes Kokoro 82M (`kokoro-82m`) is an 82M-parameter text-to-speech model served on PolarGrid edge nodes via Triton's `python` backend. It is a **preset-voice** model — pick one of a fixed catalog of named voices — which makes it the low-latency counterpart to [`tada-3b-ml`](/models/tada-3b-ml)'s voice-cloning. It is co-resident on the voice pod with [`whisper-large-v3-turbo`](/models/whisper-large-v3-turbo) and [`cohere-transcribe-03-2026`](/models/cohere-transcribe-03-2026) — see [`backend/edge-production-setup/CLAUDE.md`](https://github.com/PolarGrid-AI/polargrid-monorepo/blob/main/backend/edge-production-setup/CLAUDE.md) for the pod layout. * **HF repo:** [`hexgrad/Kokoro-82M`](https://huggingface.co/hexgrad/Kokoro-82M) * **Modality:** Text-to-Speech (streaming) * **Backend:** Triton `python` (voice pod) * **Parameters:** 82M - **Available regions:** all regions except `dfw-02` — see [Model availability](/guides/model-availability) ## Headline benchmark Kokoro exposes a chunked-HTTP streaming transport for `/v1/audio/speech`. | Measurement | p50 | p95 | | -------------------------------------------------- | ------------------- | ------- | | **End-to-end TTFA (with network)** | **158 ms** | 196 ms | | **Server-only TTFA (gateway → first triton byte)** | **46 ms** | 63 ms | | *Network leg of TTFA (e2e − server)* | *109 ms* | 134 ms | | Full-utterance latency (TTLB, client wall-clock) | 696 ms | 1025 ms | | Real-time factor (RTF) | 0.100 | 0.149 | | streaming\_verdict | streaming (100/100) | — | *Streaming `/v1/audio/speech` (`stream: true`, `pcm`, voice `bm_george`), 100 runs against `https://api.yvr-02.edge.polargrid.ai`, captured 2026-06-02 from a Vancouver-area laptop over the public internet. TTFA is the time to the first audio byte arriving at the client — identical to TTFB since the response body is raw PCM. Server-only TTFA comes from the `X-Pg-First-Byte-Ms` response header ([PR #507](https://github.com/PolarGrid-AI/polargrid-monorepo/pull/507)), the gateway's measured time to the first PCM chunk returned by triton. Total synthesis time (TTLB) is not exposed via header and stays a client-side wall-clock number. RTF = synthesis wall-clock ÷ audio duration; below 1.0 is faster than real time. All 100/100 runs returned a `streaming` verdict (54–234 chunks per utterance). Raw runs: [`benchmarks/yvr-02-2026-06-02/kokoro-82m/`](https://github.com/PolarGrid-AI/polargrid-monorepo/blob/main/benchmarks/yvr-02-2026-06-02/kokoro-82m/kokoro-82m_bench.json). Harness: [`bench/kokoro-82m/`](https://github.com/PolarGrid-AI/polargrid-monorepo/tree/main/backend/edge-production-setup/bench/kokoro-82m).* ## How this compares Same node, same harness, same `/v1/audio/speech` streaming surface as the [`tada-3b-ml`](/models/tada-3b-ml) bench in `benchmarks/yvr-02-2026-05-27/`: | Model | server TTFA p50 | e2e TTFA p50 | e2e TTLB p50 | RTF p50 | | ---------------------- | --------------- | ------------ | ------------ | --------- | | `tada-3b-ml` (3B) | 238 ms | 352 ms | 919 ms | 0.164 | | **`kokoro-82m` (82M)** | **46 ms** | **158 ms** | **696 ms** | **0.100** | Kokoro's 82M model synthesizes the first audio chunk \~5× faster server-side (46 vs 238 ms) and finishes the full utterance sooner at a lower real-time factor. The \~109 ms network leg is identical across both — same laptop, same POP. Pick kokoro for lowest-latency synthesis from a fixed voice catalog; pick tada when you need a specific cloned voice or a non-English language. For external-provider TTS comparisons (Cartesia, ElevenLabs, Hume), see the [`tada-3b-ml` card](/models/tada-3b-ml#how-this-compares). ## Quickstart Edge endpoints accept your raw `pg_*` API key as a bearer token — no token exchange. See [Authentication](/authentication). Replace `` with your edge region, or discover the nearest one via the [autorouter](/api-reference/overview#picking-a-region). ```bash cURL theme={null} curl -X POST https://api..edge.polargrid.ai/v1/audio/speech \ -H "Authorization: Bearer $POLARGRID_API_KEY" \ -H "Content-Type: application/json" \ --no-buffer \ -d '{ "model": "kokoro-82m", "input": "Hello from PolarGrid.", "voice": "bm_george", "response_format": "pcm", "stream": true }' \ --output speech.pcm ``` ```javascript JavaScript theme={null} import { PolarGrid } from "@polargrid/polargrid-sdk"; const client = await PolarGrid.create({ apiKey: process.env.POLARGRID_API_KEY }); for await (const chunk of client.textToSpeechStream({ model: "kokoro-82m", input: "Hello from PolarGrid.", voice: "bm_george", responseFormat: "opus", })) { audioPlayer.appendChunk(chunk); } ``` ```python Python theme={null} from polargrid import PolarGrid client = await PolarGrid.create(api_key="pg_...") async for chunk in client.text_to_speech_stream({ "model": "kokoro-82m", "input": "Hello from PolarGrid.", "voice": "bm_george", "response_format": "opus", }): audio_player.append_chunk(chunk) ``` ## Capabilities | Field | Value | | --------------- | ---------------------------------------------------------------------------------------------------------- | | Endpoint | `POST /v1/audio/speech` | | Audio output | 24 kHz, 16-bit, mono | | Streaming | Yes — chunked HTTP, `pcm` and `opus` (`stream: true`); audio delivered incrementally as synthesis proceeds | | Batch formats | `pcm`, `wav`, `mp3` | | Voice model | Fixed catalog of named preset voices (no cloning) | | `speed` control | `0.25`–`4.0` multiplier | | Max batch size | 1 | `voice_transcript` and `language` are `tada-3b-ml`-only fields and are ignored by `kokoro-82m`. ## Voices — preset catalog Kokoro uses **named preset voices**, not reference-clip cloning. The PolarGrid SDKs expose eight presets: | Voice ID | Accent / gender | | ------------- | ------------------------ | | `af_bella` | American English, female | | `af_sarah` | American English, female | | `am_adam` | American English, male | | `am_michael` | American English, male | | `bf_emma` | British English, female | | `bf_isabella` | British English, female | | `bm_george` | British English, male | | `bm_lewis` | British English, male | `voice` is required; the PolarGrid SDKs and CLI default to `af_bella`. An invalid voice name returns `502 Bad Gateway` (synthesis failure), never an empty `200`. See the [Text-to-Speech API reference](/api-reference/text-to-speech#voices) and the [Voice AI guide](/guides/voice) for the full upstream voice list. ## Streaming Pass `stream: true` for chunked audio over a single HTTP response. Streaming formats are `pcm` (default for raw HTTP callers) and `opus`; the PolarGrid SDKs default streaming requests to `opus`. Requesting `wav` or `mp3` with `stream: true` returns `400 Bad Request`. Audio is delivered incrementally as kokoro's pipeline produces it — the bench above observed 54–234 PCM chunks per utterance with a `streaming` verdict on every run, so the first audio arrives well before synthesis finishes. See the [Text-to-Speech API reference](/api-reference/text-to-speech#streaming) for the full streaming contract — response headers, truncated-stream detection, and the per-format table. ## Model identifier Call this model with the canonical id `kokoro-82m` at `/v1/audio/speech`. It has no short alias. The HuggingFace repo id `hexgrad/Kokoro-82M` is accepted at `/v1/models/load` for hot-loading but does not resolve at inference time. ## Notes * License: [Apache 2.0](https://huggingface.co/hexgrad/Kokoro-82M). * For a specific cloned voice or a non-English language, use [`tada-3b-ml`](/models/tada-3b-ml) — kokoro is the choice for lowest-latency synthesis from a fixed English voice catalog. ## See also * [Text-to-Speech API](/api-reference/text-to-speech) — endpoint reference, formats, streaming contract * [Voice AI guide](/guides/voice) — building voice agents on PolarGrid * [Authentication](/authentication) — using your `pg_*` API key * [`/v1/models`](/api-reference/models) — list all available models