Ollama adds local text-to-speech, 100x faster than real time on Apple Silicon

Ollama released version 0.40.11 with local text-to-speech support, starting with Phonon, a family of small speech models from Gradium, available on macOS with Windows and Linux support coming soon. On a MacBook Pro with M5 Max, Ollama's MLX-accelerated implementation ran 35% faster than Gradium's own runtime while matching the reference Hugging Face Transformers implementation's word error rate, and the models are served through an OpenAI-compatible /v1/audio/speech endpoint. Phonon ships in English plus 40M-parameter French, German, Spanish, Portuguese and multilingual variants, with the base model under Apache 2.0 and the 40M models under CC BY-NC 4.0, which limits them to noncommercial use.

Speech models in Ollama October 24, 2026 Ollama can now turn text into speech. The first speech model is Phonon https://ollama.com/library/phonon , a family of small, state-of-the-art text-to-speech models from Gradium https://gradium.ai . Speech models are now available for macOS, with Windows and Linux support coming soon. ollama run phonon "Hello from Ollama." Performance on Apple Silicon On Apple Silicon, Ollama is accelerated by MLX, Apple’s machine learning framework, for state-of-the-art throughput. On a MacBook Pro with M5 Max, Ollama was 35% faster than the next fastest engine, Gradium’s own runtime. Ollama’s implementation is just as accurate, matching the word error rate of the reference implementation in Hugging Face Transformers: Voices Choose a voice with --voice , or voice in the API: ollama run phonon --voice Hadley "Hello from Ollama." The voices come from Gradium’s voice catalog https://huggingface.co/gradium/phonon-voices . ollama show phonon lists them all. Languages | Model | Language | |---|---| | phonon | English | | phonon:40m-fr | French | | phonon:40m-de | German | | phonon:40m-es | Spanish | | phonon:40m-pt | Portuguese | | phonon:40m-multilingual | All five | phonon is released under Apache 2.0. The 40M models are released under CC BY-NC 4.0, which limits them to noncommercial use. Read replies aloud Pipe a chat model’s reply into Phonon. Text is spoken as it arrives, so the reply starts playing after its first sentence: ollama run gemma4 --hidethinking "Tell me a fun fact about owls in two sentences." | ollama run phonon Run ollama run phonon with no text to type lines at a prompt, or redirect the output to save a WAV file: ollama run phonon "Save this to a file." speech.wav API Phonon works with the OpenAI-compatible /v1/audio/speech endpoint, so existing code that uses the OpenAI SDK only needs a new base URL. curl http://localhost:11434/v1/audio/speech \ -H "Content-Type: application/json" \ -d '{ "model": "phonon", "voice": "Zoey", "input": "Hello from Ollama." }' --output speech.wav python from openai import OpenAI client = OpenAI base url="http://localhost:11434/v1", api key="ollama" with client.audio.speech.with streaming response.create model="phonon", voice="Zoey", input="Hello from Ollama.", response format="wav", as response: response.stream to file "speech.wav" python import fs from "node:fs" import OpenAI from "openai" const openai = new OpenAI { baseURL: "http://localhost:11434/v1", apiKey: "ollama" } const response = await openai.audio.speech.create { model: "phonon", voice: "Zoey", input: "Hello from Ollama.", response format: "wav", } fs.writeFileSync "speech.wav", Buffer.from await response.arrayBuffer The response streams while the audio is generated, so it can play right away: curl -sN http://localhost:11434/v1/audio/speech \ -H "Content-Type: application/json" \ -d '{"model": "phonon", "input": "Playback starts right away."}' \ | ffplay -nodisp -autoexit -loglevel error - Audio is 24 kHz mono, returned as WAV by default or as raw 16-bit samples with "response format": "pcm" . Get started Speech models run on Apple Silicon Macs. Download Ollama https://ollama.com/download 0.40.11 or later, then pull Phonon: ollama pull phonon For more information, see: